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

    Neuronpedia

    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. 13188
    Prev
    Next
    INDEX
    Explanations

    medical terms and information related to responses, responsibility, and action

    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
    343
    +0.14
    0.6%
    739
    +0.14
    0.6%
    232
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.07
    343
    +0.14
    0.07
    288
    +0.13
    0.09
    Negative Logits
    buster
    -0.81
    piece
    -0.78
     Mour
    -0.77
    beard
    -0.77
    phabet
    -0.77
    busters
    -0.76
    WARE
    -0.76
     Catalyst
    -0.75
    WAYS
    -0.69
    EngineDebug
    -0.69
    POSITIVE LOGITS
    aband
    1.11
    assion
    1.10
    resent
    1.05
    itable
    1.05
    inished
    1.04
    idge
    1.02
    odied
    1.00
    ionage
    0.99
    aced
    0.97
    aces
    0.95
    Activations Density 0.812%

    No Known Activations