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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4154
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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
    91
    +0.09
    0.5%
    586
    +0.08
    0.4%
    447
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.09
    0.23
    45
    +0.08
    0.03
    598
    +0.08
    0.03
    Negative Logits
    enhagen
    -0.76
    interstitial
    -0.75
     ¶
    -0.68
    vasive
    -0.66
    vertisement
    -0.63
     infiltrated
    -0.59
    ]).
    -0.59
    FontSize
    -0.58
     faculty
    -0.56
     faked
    -0.56
    POSITIVE LOGITS
    Reviewer
    1.27
    udos
    0.77
     reviewer
    0.73
    Nit
    0.71
    Mods
    0.71
    RIP
    0.70
    Classic
    0.70
    Quote
    0.69
    Winner
    0.68
    ----------------------------------------------------------------
    0.66
    Activations Density 8.842%

    No Known Activations