© 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. 36719
    Prev
    Next
    INDEX
    Explanations

    discussions or opinions on historical events and societal dynamics

    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
    +0.15
    0.8%
    393
    +0.14
    0.7%
    566
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.15
    0.17
    566
    +0.14
    0.15
    102
    +0.11
    0.18
    Negative Logits
    igent
    -0.60
    ampa
    -0.59
    achu
    -0.59
    entric
    -0.58
    lev
    -0.58
    forward
    -0.56
    ethy
    -0.55
     Hague
    -0.55
    wall
    -0.55
    Footnote
    -0.54
    POSITIVE LOGITS
    hes
    0.96
    wolves
    0.90
     originally
    0.87
    wolf
    0.80
     conceived
    0.72
     instrumental
    0.71
     formerly
    0.70
     initially
    0.68
    hers
    0.67
     born
    0.66
    Activations Density 7.961%

    No Known Activations