© 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. 36733
    Prev
    Next
    INDEX
    Explanations

    political terms and discussions

    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
    +0.37
    1.8%
    674
    +0.08
    0.4%
    745
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.37
    0.64
    77
    +0.08
    0.12
    608
    +0.08
    0.35
    Negative Logits
     Whitman
    -0.85
     Slate
    -0.83
     Boone
    -0.79
     Harbor
    -0.78
     Everett
    -0.78
     Gotham
    -0.77
     Brooklyn
    -0.76
     Lovecraft
    -0.76
     Hartford
    -0.76
    Ohio
    -0.75
    POSITIVE LOGITS
     Malays
    1.00
     learnt
    0.98
    jriwal
    0.97
     organise
    0.92
     Daesh
    0.92
     authorised
    0.92
     analyse
    0.91
     chall
    0.90
     util
    0.89
     Tamil
    0.89
    Activations Density 57.784%

    No Known Activations