© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    instances of the word "enough" in various contexts

    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
    375
    +0.15
    0.5%
    222
    +0.14
    0.5%
    608
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.15
    0.04
    513
    +0.14
    0.04
    375
    +0.14
    0.03
    Negative Logits
    amon
    -1.02
     Myster
    -0.97
    abad
    -0.93
    folk
    -0.92
    ificate
    -0.92
     foss
    -0.91
     POLITICO
    -0.88
    eston
    -0.88
     Gh
    -0.88
    tell
    -0.86
    POSITIVE LOGITS
    HUD
    1.00
    osponsors
    0.98
     calories
    0.98
    GoldMagikarp
    0.94
    natureconservancy
    0.93
    ones
    0.92
     ILCS
    0.89
     ammunition
    0.89
    Enough
    0.89
     allowance
    0.88
    Activations Density 0.543%

    No Known Activations