© 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 1536
    9. 8-RES_FS1536-JB
    11. 24
    Prev
    Next
    INDEX
    Explanations

    details related to community activities and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    514
    +0.12
    0.6%
    759
    +0.12
    0.5%
    426
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    514
    +0.12
    0.25
    352
    +0.12
    0.25
    759
    +0.11
    0.24
    Negative Logits
     Palest
    -0.83
     guiActiveUnfocused
    -0.82
    Buyable
    -0.71
     RAD
    -0.64
     hors
    -0.64
    ozy
    -0.64
    è£ħ
    -0.64
     Networks
    -0.63
     CLR
    -0.62
     GPS
    -0.61
    POSITIVE LOGITS
    £
    0.99
    should
    0.97
    ¼
    0.97
    could
    0.93
    ¤
    0.92
    ¢
    0.92
    º
    0.90
    Ń
    0.89
    ///
    0.88
    Ĵ
    0.87
    Activations Density 1.096%

    No Known Activations