© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2455
    Prev
    Next
    INDEX
    Explanations

    words related to leadership roles in organizational settings, such as vice president, managing director, and senior director

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    104
    +0.14
    0.5%
    399
    +0.14
    0.5%
    63
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.13
    508
    +0.14
    0.08
    752
    +0.14
    0.09
    Negative Logits
     interfered
    -0.91
     succeed
    -0.89
     safely
    -0.88
     succeeding
    -0.88
     intervening
    -0.88
    apo
    -0.88
    anism
    -0.87
    infeld
    -0.87
     purposely
    -0.87
     repaid
    -0.86
    POSITIVE LOGITS
    director
    1.61
     director
    1.42
     counsel
    1.34
     coordinator
    1.30
     curator
    1.26
     assistant
    1.21
     analyst
    1.20
     spokesperson
    1.20
     attorney
    1.17
     correspondent
    1.17
    Activations Density 1.672%

    No Known Activations