© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9236
    Prev
    Next
    INDEX
    Explanations

    discussion points or arguments related to a specific topic, focusing more strongly on specific discussions

    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
    689
    +0.12
    0.5%
    195
    +0.11
    0.5%
    724
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    689
    +0.12
    0.04
    541
    +0.11
    0.04
    679
    +0.10
    0.04
    Negative Logits
    ingham
    -0.65
    cot
    -0.64
    activated
    -0.62
    cession
    -0.62
    ctors
    -0.60
     Clicker
    -0.60
    ateurs
    -0.59
    iw
    -0.59
    mercial
    -0.59
    pan
    -0.58
    POSITIVE LOGITS
     herein
    1.17
     above
    1.04
     therein
    1.00
     below
    0.97
     by
    0.96
     elsewhere
    0.94
     hereafter
    0.87
     here
    0.87
     separately
    0.85
     supra
    0.85
    Activations Density 0.134%

    No Known Activations