© 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 24576
    9. 8-RES_FS24576-JB
    11. 18816
    Prev
    Next
    INDEX
    Explanations

    websites or links in text

    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
    766
    +0.12
    0.5%
    107
    +0.11
    0.5%
    412
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.12
    0.03
    284
    +0.11
    0.03
    766
    +0.10
    0.03
    Negative Logits
     Bei
    -0.79
     CARD
    -0.72
     Advertisement
    -0.71
     TAMADRA
    -0.70
    ThumbnailImage
    -0.68
     premature
    -0.67
    ï¸
    -0.67
     Caption
    -0.66
     Maher
    -0.66
    GGGGGGGG
    -0.66
    POSITIVE LOGITS
    cdn
    1.36
    online
    1.23
    project
    1.01
    nexus
    1.00
    pedia
    1.00
    forums
    0.99
    oft
    0.97
    research
    0.97
    planet
    0.97
    ibrary
    0.96
    Activations Density 0.067%

    No Known Activations