© 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. 40459
    Prev
    Next
    INDEX
    Explanations

    historical dates as well as periods in history and specific historical events

    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
    +0.25
    1.0%
    744
    +0.12
    0.5%
    468
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.25
    0.14
    107
    +0.12
    0.04
    640
    +0.11
    0.16
    Negative Logits
     neighb
    -0.80
    inventoryQuantity
    -0.78
     RAID
    -0.73
     welf
    -0.71
     pse
    -0.68
     warr
    -0.68
     CVE
    -0.67
    ciating
    -0.67
    notations
    -0.64
     masc
    -0.61
    POSITIVE LOGITS
     onwards
    0.83
    çļ
    0.81
    -'
    0.80
     onward
    0.72
     MacArthur
    0.68
    tel
    0.67
    ffe
    0.67
    meier
    0.66
     Bomber
    0.66
    lander
    0.66
    Activations Density 7.002%

    No Known Activations