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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5354
    Prev
    Next
    INDEX
    Explanations

    terms related to alt-right ideologies and movements

    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
    +0.31
    1.1%
    311
    +0.18
    0.6%
    701
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.31
    0.08
    701
    +0.18
    0.05
    57
    +0.18
    0.04
    Negative Logits
    ecause
    -1.14
    BLE
    -1.10
    enegger
    -0.99
    hips
    -0.97
    loo
    -0.95
    nces
    -0.92
    #$#$
    -0.91
    mbudsman
    -0.89
    ³³³³³³³³³³³³³³³³
    -0.89
    manship
    -0.88
    POSITIVE LOGITS
    itude
    1.66
    ogether
    1.61
    itudes
    1.59
    itud
    1.55
    itudinal
    1.48
    imore
    1.32
    uve
    1.14
    imates
    1.11
    imately
    1.10
    imeter
    1.06
    Activations Density 0.721%

    No Known Activations