© 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 EvalsExportsAPI 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 959
    Prev
    Next
    INDEX
    Explanations

    topics related to government policies, welfare programs, political discussions, and financial transactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    288
    +0.18
    0.6%
    536
    +0.14
    0.5%
    317
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.18
    0.09
    430
    +0.14
    0.15
    618
    +0.12
    0.11
    Negative Logits
     Wilmington
    -0.98
    furt
    -0.98
     Webster
    -0.97
    Weiss
    -0.96
     Lexington
    -0.94
     Beacon
    -0.93
     Bonnie
    -0.88
    ylum
    -0.87
     Portsmouth
    -0.87
     raven
    -0.86
    POSITIVE LOGITS
     Sharma
    1.73
     Pradesh
    1.54
     Singh
    1.51
     Patel
    1.43
    jriwal
    1.41
     Kumar
    1.34
     Bhar
    1.33
     Modi
    1.32
    umbai
    1.32
     Raj
    1.32
    Activations Density 7.645%

    No Known Activations