© 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. 6658
    Prev
    Next
    INDEX
    Explanations

    legal or policy-related terms and instructions

    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
    61
    +0.10
    0.5%
    505
    +0.10
    0.5%
    512
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.10
    0.03
    373
    +0.10
    -0.01
    236
    +0.09
    0.02
    Negative Logits
    ORPG
    -0.62
     bip
    -0.61
     typh
    -0.61
    EMENT
    -0.58
     breakthrough
    -0.57
    lex
    -0.57
     Luck
    -0.57
     clue
    -0.56
    CHR
    -0.56
     Rolls
    -0.55
    POSITIVE LOGITS
    >)
    0.82
    iris
    0.73
     salv
    0.68
    ubes
    0.65
    aser
    0.65
     Seller
    0.64
    hur
    0.64
    wcsstore
    0.63
    ģĸ
    0.63
    minus
    0.63
    Activations Density 0.106%

    No Known Activations