© 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. 6119
    Prev
    Next
    INDEX
    Explanations

    words related to mistreatment and medical symptoms

    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
    +0.24
    0.8%
    739
    +0.17
    0.6%
    459
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.24
    0.06
    326
    +0.17
    0.05
    128
    +0.15
    0.04
    Negative Logits
    à¼
    -0.92
    Books
    -0.91
    phrine
    -0.89
    jriwal
    -0.89
    pta
    -0.88
    thodox
    -0.86
    VERSION
    -0.83
    MIT
    -0.83
    versions
    -0.83
    ITAL
    -0.82
    POSITIVE LOGITS
    reatment
    1.60
    reated
    1.33
    aken
    1.29
    reating
    1.23
    rans
    1.18
    arget
    1.13
    mallow
    1.11
    resses
    1.10
    ake
    1.10
    lust
    1.09
    Activations Density 0.564%

    No Known Activations