© 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. 9839
    Prev
    Next
    INDEX
    Explanations

    words related to water and its various properties and uses

    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
    739
    +0.11
    0.5%
    289
    +0.10
    0.5%
    67
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    564
    +0.11
    0.04
    289
    +0.10
    0.02
    592
    +0.09
    0.03
    Negative Logits
    eering
    -0.87
    Reloaded
    -0.76
    ures
    -0.69
    Files
    -0.69
     Amend
    -0.69
    ificant
    -0.67
    ature
    -0.63
    doms
    -0.63
    uate
    -0.63
    urations
    -0.61
    POSITIVE LOGITS
    melon
    1.75
    tight
    1.21
    colour
    1.15
    falls
    1.14
    mel
    1.04
     soluble
    0.96
    proof
    0.95
    bowl
    0.94
    borne
    0.93
    color
    0.92
    Activations Density 0.088%

    No Known Activations