© 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. 13719
    Prev
    Next
    INDEX
    Explanations

    names of places and people

    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
    379
    +0.10
    0.5%
    326
    +0.10
    0.5%
    307
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.20
    288
    +0.10
    0.20
    568
    +0.10
    0.05
    Negative Logits
    itutional
    -0.79
    endon
    -0.70
    oyer
    -0.67
    brance
    -0.66
    ivity
    -0.65
    ilda
    -0.64
     Citation
    -0.63
    imore
    -0.62
    icity
    -0.62
    abeth
    -0.60
    POSITIVE LOGITS
    vec
    0.90
    geon
    0.84
    lator
    0.83
    cles
    0.80
    pathic
    0.78
    scope
    0.78
    bind
    0.76
    pathy
    0.76
    bull
    0.74
    ffe
    0.73
    Activations Density 6.718%

    No Known Activations