© 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. 340
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, specifically places ending in 'ish'

    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
    709
    +0.12
    0.5%
    695
    +0.12
    0.5%
    71
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    709
    +0.12
    0.02
    464
    +0.11
    0.02
    Negative Logits
     heartbeat
    -0.67
     rall
    -0.67
    wcs
    -0.65
    agonist
    -0.63
     inst
    -0.60
    orthern
    -0.60
    oples
    -0.60
    ļéĨĴ
    -0.60
     Reloaded
    -0.59
    heric
    -0.59
    POSITIVE LOGITS
    onest
    1.02
    liest
    0.93
    nesses
    0.88
    tml
    0.88
    ttp
    0.86
    onen
    0.86
    chev
    0.85
    ings
    0.84
    »Ĵ
    0.84
    imaru
    0.84
    Activations Density 0.113%

    No Known Activations