© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 6572
    Prev
    Next
    INDEX
    Explanations

    political figures and actions or discussions related to public policy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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%
    615
    +0.10
    0.5%
    35
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.11
    0.02
    286
    +0.10
    0.02
    31
    +0.10
    0.02
    Negative Logits
     factor
    -0.71
    ahime
    -0.71
    phal
    -0.66
     Brist
    -0.65
     factors
    -0.64
     blight
    -0.63
     nature
    -0.61
    istically
    -0.61
     darker
    -0.61
     trap
    -0.60
    POSITIVE LOGITS
    orters
    1.47
    orter
    1.27
    rint
    1.27
    utation
    1.23
    ository
    1.20
    orted
    1.20
    ublic
    1.19
    rieve
    1.18
    ositories
    1.13
    atri
    1.12
    Activations Density 0.016%

    No Known Activations