© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 36899
    Prev
    Next
    INDEX
    Explanations

    descriptive words and phrases related to military operations and infrastructure

    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
    +0.23
    1.1%
    113
    +0.12
    0.5%
    584
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.23
    0.13
    125
    +0.12
    0.12
    70
    +0.10
    0.14
    Negative Logits
    storms
    -0.62
    ipeg
    -0.61
     heights
    -0.60
    aya
    -0.58
     Flavoring
    -0.57
     storm
    -0.57
    rouse
    -0.57
     storms
    -0.56
    Storm
    -0.56
    talk
    -0.55
    POSITIVE LOGITS
     geographically
    0.79
    entious
    0.78
    ependent
    0.78
    hematically
    0.77
    ertodd
    0.75
     solely
    0.72
     statically
    0.67
    ptin
    0.66
    rig
    0.66
    igating
    0.65
    Activations Density 9.173%

    No Known Activations