© 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. 389
    Prev
    Next
    INDEX
    Explanations

    Congressional representatives and discussions of political matters

    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
    223
    +0.11
    0.5%
    35
    +0.10
    0.4%
    615
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.11
    0.03
    31
    +0.10
    0.03
    286
    +0.10
    0.02
    Negative Logits
     factor
    -0.73
    phal
    -0.70
    ahime
    -0.70
     factors
    -0.66
    istically
    -0.66
     Brist
    -0.64
     nature
    -0.64
     underpin
    -0.61
     blight
    -0.61
     Dwar
    -0.58
    POSITIVE LOGITS
    orters
    1.39
    orter
    1.25
    rint
    1.21
    rieve
    1.19
    utation
    1.17
    ository
    1.16
    ublic
    1.14
    orted
    1.14
    ositories
    1.10
    atri
    1.09
    Activations Density 0.047%

    No Known Activations