Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 12000
    Prev
    Next
    INDEX
    Explanations

    references to government entities and political affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    262
    +0.11
    0.5%
    620
    +0.10
    0.4%
    711
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.08
    288
    +0.10
    0.08
    547
    +0.10
    0.04
    Negative Logits
     glim
    -0.67
    Magikarp
    -0.62
    ortun
    -0.59
    MAS
    -0.55
    ITNESS
    -0.55
    yss
    -0.54
     continued
    -0.54
    igham
    -0.53
    Hop
    -0.53
     priesthood
    -0.52
    POSITIVE LOGITS
    .''.
    1.02
    _.
    0.96
    ).
    0.92
    .ãĢį
    0.90
    .).
    0.90
    .
    0.88
    *.
    0.88
    .''
    0.87
    .�
    0.85
    .</
    0.84
    Activations Density 0.556%

    No Known Activations