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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36031
    Prev
    Next
    INDEX
    Explanations

    information related to real-world events and incidents, such as natural disasters, political figures, legal cases, and historical contexts

    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
    +0.22
    1.1%
    69
    +0.13
    0.6%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.22
    0.23
    6
    +0.13
    0.18
    679
    +0.11
    0.20
    Negative Logits
    authorized
    -0.69
    ozo
    -0.67
    ofer
    -0.66
    offer
    -0.66
    pard
    -0.65
    ivable
    -0.65
    pack
    -0.64
    oes
    -0.64
    osing
    -0.63
    Initialized
    -0.63
    POSITIVE LOGITS
     Photograph
    0.85
     Ahead
    0.82
     Dame
    0.80
     Pict
    0.77
     ï
    0.75
     Gian
    0.74
     Seym
    0.74
     Osw
    0.72
     Above
    0.72
     Photos
    0.71
    Activations Density 7.284%

    No Known Activations