© 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 12288
    9. 8-RES_FS12288-JB
    11. 482
    Prev
    Next
    INDEX
    Explanations

    words related to certainty or inevitability

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    370
    +0.14
    0.6%
    377
    +0.11
    0.5%
    365
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.02
    370
    +0.11
    0.01
    365
    +0.11
    0.01
    Negative Logits
    issance
    -0.89
    amera
    -0.70
    HAEL
    -0.68
    zanne
    -0.68
    visors
    -0.65
    cano
    -0.65
    ciation
    -0.65
    PE
    -0.64
    ————
    -0.63
    STEM
    -0.63
    POSITIVE LOGITS
    less
    1.13
    lessly
    0.99
    ging
    0.95
    binding
    0.90
    sym
    0.87
    fold
    0.86
    pipe
    0.84
    unin
    0.83
    ged
    0.82
    lock
    0.80
    Activations Density 0.098%

    No Known Activations