© 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. 4211
    Prev
    Next
    INDEX
    Explanations

    - different entities or entities interacting with each other

    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
    447
    +0.19
    1.1%
    570
    +0.08
    0.5%
    326
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.19
    0.29
    743
    +0.08
    0.09
    255
    +0.08
    0.13
    Negative Logits
    lance
    -0.55
    lus
    -0.52
    lov
    -0.52
     Indust
    -0.52
    indust
    -0.52
    asta
    -0.51
    LER
    -0.50
    vich
    -0.50
    undown
    -0.49
    gow
    -0.48
    POSITIVE LOGITS
    fold
    0.80
     hundred
    0.78
     thousand
    0.78
     dimensional
    0.78
     dozen
    0.73
     consecutive
    0.73
     thirds
    0.73
     pairs
    0.73
     feet
    0.73
    teen
    0.71
    Activations Density 14.029%

    No Known Activations