© 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 Local
    9. 6-RES_SCL-AJT
    11. 31651
    Prev
    Next
    INDEX
    Explanations

    technical details and instructions related to software programming and configuration

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.19
    1.2%
    497
    +0.10
    0.6%
    455
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.19
    0.29
    643
    +0.10
    0.09
    455
    +0.09
    0.20
    Negative Logits
    TIME
    -0.57
    Kings
    -0.56
    Roy
    -0.51
    Honest
    -0.51
    truth
    -0.51
     Principles
    -0.50
    Charlie
    -0.49
     Moments
    -0.48
     Pon
    -0.48
    BILL
    -0.48
    POSITIVE LOGITS
     necessarily
    0.88
    icably
    0.78
    epad
    0.76
    icable
    0.69
     automatically
    0.65
     bother
    0.64
     interpol
    0.63
     exclude
    0.63
     permitted
    0.61
     removable
    0.60
    Activations Density 13.849%

    No Known Activations