© 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. 35462
    Prev
    Next
    INDEX
    Explanations

    notifications for subscriptions or newsletters

    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
    314
    +0.11
    0.6%
    257
    +0.09
    0.5%
    565
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    -0.05
    498
    +0.09
    0.09
    95
    +0.08
    0.04
    Negative Logits
     Catalyst
    -0.62
     hurd
    -0.59
     Examination
    -0.52
     tant
    -0.52
    fman
    -0.51
     reckoned
    -0.51
    MET
    -0.51
     hormonal
    -0.50
    posted
    -0.49
     mas
    -0.48
    POSITIVE LOGITS
    igers
    0.60
     Cancel
    0.53
    ecast
    0.51
    iframe
    0.51
    Copy
    0.50
    plugins
    0.50
    Plex
    0.49
    ims
    0.49
     Fill
    0.48
     Thumbnails
    0.48
    Activations Density 6.554%

    No Known Activations