© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40778
    Prev
    Next
    INDEX
    Explanations

    mentions of specific historical events and time periods, especially related to World War II

    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
    +0.27
    1.4%
    620
    +0.09
    0.4%
    346
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.27
    0.05
    546
    +0.09
    0.10
    721
    +0.08
    0.08
    Negative Logits
    BOOK
    -0.66
     snipp
    -0.66
    Tar
    -0.64
    Jar
    -0.63
    Weak
    -0.60
    à
    -0.60
    Tile
    -0.59
    Word
    -0.57
    Journal
    -0.57
    Brew
    -0.56
    POSITIVE LOGITS
     era
    0.71
    hower
    0.71
     Memorial
    0.68
     Syndrome
    0.67
     Anniversary
    0.66
     Veteran
    0.66
     Bomber
    0.64
     Veterans
    0.64
     Panzer
    0.63
     veterans
    0.61
    Activations Density 12.481%

    No Known Activations