© 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. 31294
    Prev
    Next
    INDEX
    Explanations

    names or entities in news articles and interviews

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    659
    +0.12
    0.6%
    126
    +0.10
    0.5%
    511
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.17
    232
    +0.10
    0.10
    511
    +0.10
    0.11
    Negative Logits
    Ö¼
    -0.87
    âĶĢâĶĢ
    -0.81
    incial
    -0.74
    REDACTED
    -0.72
    士
    -0.71
    ISION
    -0.70
    èĢħ
    -0.67
    manship
    -0.66
     Samoa
    -0.65
     Enrique
    -0.64
    POSITIVE LOGITS
    verson
    0.93
    monds
    0.82
    burn
    0.79
    isner
    0.74
    bright
    0.74
    antz
    0.72
    stad
    0.71
    gren
    0.71
    riger
    0.70
    nington
    0.68
    Activations Density 6.306%

    No Known Activations