© 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. 6034
    Prev
    Next
    INDEX
    Explanations

    reports of violent incidents and criminal activities

    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
    430
    +0.17
    0.8%
    679
    +0.11
    0.5%
    232
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.17
    0.11
    430
    +0.11
    0.11
    679
    +0.11
    0.10
    Negative Logits
    à¼
    -0.72
     manufact
    -0.72
     ecosystem
    -0.71
     enthusi
    -0.71
     tremend
    -0.70
    icons
    -0.70
     fleets
    -0.69
    inki
    -0.68
     achievable
    -0.68
     realism
    -0.67
    POSITIVE LOGITS
     His
    1.41
     Prosecutors
    1.30
     He
    1.24
     Previously
    1.14
     According
    1.13
     She
    1.11
     Investigators
    1.09
     Witnesses
    1.09
     Others
    1.08
     Earlier
    1.08
    Activations Density 0.427%

    No Known Activations