© 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 EvalsExportsAPI 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. 7049
    Prev
    Next
    INDEX
    Explanations

    phrases related to listening, conversation, public speaking, and interacting with others

    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
    393
    +0.43
    1.5%
    659
    +0.15
    0.5%
    587
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.43
    0.09
    393
    +0.15
    0.09
    0
    +0.15
    0.08
    Negative Logits
    lihood
    -0.98
    piration
    -0.92
    panel
    -0.88
    ¶
    -0.85
    ancial
    -0.83
     Powered
    -0.83
    uty
    -0.83
    rss
    -0.81
    emo
    -0.81
    cess
    -0.81
    POSITIVE LOGITS
    romeda
    1.20
    rogen
    1.17
     hopefully
    1.15
     consequently
    1.13
     therefore
    1.06
     then
    0.96
     maybe
    0.95
     vice
    0.94
     hence
    0.92
     presumably
    0.92
    Activations Density 1.028%

    No Known Activations