© 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. 32907
    Prev
    Next
    INDEX
    Explanations

    references to historical events related to World War II, particularly regarding Nazi Germany, Adolf Hitler, the Holocaust, and Nazi activities and individuals

    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
    +0.18
    0.9%
    218
    +0.15
    0.7%
    288
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.18
    0.07
    10
    +0.15
    0.06
    218
    +0.14
    0.05
    Negative Logits
    pring
    -0.78
    pole
    -0.78
    ately
    -0.75
    Downloadha
    -0.74
    ttes
    -0.74
    tis
    -0.72
    notes
    -0.70
    oner
    -0.69
    trak
    -0.67
    LESS
    -0.67
    POSITIVE LOGITS
     Hitler
    0.84
     salute
    0.82
     Youth
    0.82
    chwitz
    0.77
     Reich
    0.76
     Holocaust
    0.75
     sympath
    0.73
     Germany
    0.71
     Adolf
    0.69
     dictator
    0.69
    Activations Density 8.267%

    No Known Activations