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

    Neuronpedia

    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. 5658
    Prev
    Next
    INDEX
    Explanations

    mentions of political events and figures

    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
    398
    +0.15
    0.5%
    706
    +0.15
    0.5%
    631
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.06
    398
    +0.15
    0.06
    314
    +0.15
    0.01
    Negative Logits
     contrace
    -0.95
     Skydragon
    -0.94
     taxp
    -0.94
    anism
    -0.92
     mast
    -0.90
     stakes
    -0.90
     Medals
    -0.88
     acad
    -0.85
     brim
    -0.85
     Pradesh
    -0.85
    POSITIVE LOGITS
    rency
    1.32
    ollah
    1.12
    execute
    1.07
    rique
    1.00
    uld
    0.96
    ainment
    0.94
    vention
    0.94
    repeat
    0.91
    eur
    0.91
    visual
    0.91
    Activations Density 1.108%

    No Known Activations