© 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. 7503
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming and code implementation

    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
    63
    +0.13
    0.5%
    762
    +0.12
    0.5%
    326
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.04
    30
    +0.12
    0.02
    684
    +0.12
    0.02
    Negative Logits
    eway
    -0.82
     reconc
    -0.79
     skelet
    -0.76
     corrid
    -0.75
    uman
    -0.73
    ovych
    -0.73
    emaker
    -0.72
    arcity
    -0.72
    cause
    -0.70
     Gamb
    -0.70
    POSITIVE LOGITS
     ®
    0.88
    ÃŃn
    0.88
     Tayyip
    0.77
     i
    0.76
    roit
    0.76
    BOOK
    0.75
    Whe
    0.73
    irit
    0.73
    ®
    0.72
     Mk
    0.72
    Activations Density 0.181%

    No Known Activations