© 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. 13716
    Prev
    Next
    INDEX
    Explanations

    references to rules, regulations, or stipulations

    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
    739
    +0.15
    0.8%
    447
    +0.11
    0.6%
    155
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.19
    749
    +0.11
    0.08
    52
    +0.09
    0.06
    Negative Logits
     Breath
    -0.59
     Roses
    -0.59
    ãĥīãĥ©ãĤ´ãĥ³
    -0.58
     CrossRef
    -0.57
     Tycoon
    -0.57
     confidence
    -0.54
     breath
    -0.54
    NetMessage
    -0.53
     Angry
    -0.52
     Royale
    -0.52
    POSITIVE LOGITS
     stip
    0.97
    endiary
    0.90
    ends
    0.79
    ulated
    0.79
    ulates
    0.78
    ulum
    0.75
    ulative
    0.74
    iotics
    0.74
    ilit
    0.73
    endum
    0.73
    Activations Density 6.991%

    No Known Activations