© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37274
    Prev
    Next
    INDEX
    Explanations

    terms related to ethics and bioethics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.12
    0.5%
    315
    +0.11
    0.5%
    142
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    0.01
    589
    +0.11
    0.02
    315
    +0.11
    0.01
    Negative Logits
    LESS
    -0.71
    displayText
    -0.65
     Leilan
    -0.64
    staking
    -0.63
     Ruk
    -0.63
    HF
    -0.61
     overlooking
    -0.61
     Puerto
    -0.61
     TBA
    -0.60
     duty
    -0.60
    POSITIVE LOGITS
    rencies
    1.07
    naissance
    0.97
    icist
    0.97
    alyst
    0.91
    ological
    0.90
    vironments
    0.89
    ionage
    0.88
    asma
    0.88
    ography
    0.86
    ternity
    0.86
    Activations Density 0.040%

    No Known Activations