© 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. 33051
    Prev
    Next
    INDEX
    Explanations

    expressions mentioning that something is based on certain factors or criteria

    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
    679
    +0.17
    0.7%
    447
    +0.17
    0.7%
    146
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.17
    133
    +0.17
    0.07
    146
    +0.15
    0.07
    Negative Logits
    nel
    -0.87
    shr
    -0.78
    antha
    -0.77
    osen
    -0.75
    asar
    -0.75
    ESE
    -0.73
    dra
    -0.73
     Leilan
    -0.72
    lain
    -0.70
    icut
    -0.69
    POSITIVE LOGITS
     loosely
    0.93
     upon
    0.86
     solely
    0.78
    awaru
    0.74
     certific
    0.71
     transcription
    0.69
    monary
    0.67
     paycheck
    0.67
     diligence
    0.66
    ragon
    0.66
    Activations Density 7.272%

    No Known Activations