© 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. 11052
    Prev
    Next
    INDEX
    Explanations

    legal terms and regulations

    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
    393
    +0.22
    1.0%
    385
    +0.15
    0.7%
    476
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.22
    0.12
    385
    +0.15
    0.10
    393
    +0.14
    0.09
    Negative Logits
    ricks
    -0.72
    oops
    -0.72
     billionaires
    -0.70
    tackle
    -0.68
     hardly
    -0.67
    skip
    -0.66
    LOD
    -0.66
    Bloomberg
    -0.65
    wo
    -0.65
     goodbye
    -0.65
    POSITIVE LOGITS
     respective
    1.33
     applicant
    1.30
     foregoing
    1.30
     licensee
    1.21
     purchaser
    1.17
     remainder
    1.15
     afore
    1.12
     same
    1.12
     following
    1.12
     aforementioned
    1.10
    Activations Density 0.518%

    No Known Activations