© 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. 906
    Prev
    Next
    INDEX
    Explanations

    words related to legal or ethical issues

    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
    593
    +0.11
    0.5%
    362
    +0.10
    0.5%
    173
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.08
    362
    +0.10
    0.07
    647
    +0.10
    0.05
    Negative Logits
    anooga
    -0.74
    iso
    -0.71
    Synopsis
    -0.68
    Recent
    -0.66
    äºĶ
    -0.63
    tions
    -0.62
     Carbuncle
    -0.61
    é¾įå¥ij士
    -0.60
     emerge
    -0.60
     resembles
    -0.59
    POSITIVE LOGITS
     someone
    0.72
    geries
    0.72
     nowhere
    0.66
    seless
    0.66
     legitimate
    0.65
     something
    0.64
    CE
    0.63
     purely
    0.63
    oteric
    0.63
     reputable
    0.62
    Activations Density 0.556%

    No Known Activations