© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and their actions

    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
    +0.29
    1.5%
    616
    +0.10
    0.5%
    393
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.29
    0.32
    566
    +0.10
    0.16
    128
    +0.09
    0.14
    Negative Logits
    ylon
    -0.64
    otin
    -0.64
    onite
    -0.55
    avis
    -0.55
    ata
    -0.55
    breaker
    -0.55
    poly
    -0.53
    landers
    -0.52
     Canadians
    -0.52
     Nationals
    -0.51
    POSITIVE LOGITS
     own
    0.83
     tremend
    0.67
     introductory
    0.66
     travels
    0.66
     memoir
    0.66
     Own
    0.64
     briefs
    0.61
     remarks
    0.61
     autobiography
    0.59
     endeavors
    0.58
    Activations Density 14.102%

    No Known Activations