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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 572
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    373
    +0.52
    6.1%
    481
    +0.44
    5.2%
    87
    +0.33
    4.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.52
    -0.12
    373
    +0.44
    -0.26
    756
    +0.33
    -0.15
    Negative Logits
     Âł
    -0.21
     Originally
    -0.21
    ↵Âł
    -0.20
     Âł Âł Âł Âł
    -0.20
    olina
    -0.20
    ³³³
    -0.19
     ......
    -0.19
     ³³
    -0.18
    esi
    -0.18
     Located
    -0.18
    POSITIVE LOGITS
    ichever
    0.19
     vou
    0.18
    polit
    0.17
    ueless
    0.17
     interim
    0.17
     Ec
    0.17
    iddling
    0.17
    âĢ¢âĢ¢
    0.17
    azeera
    0.17
     onward
    0.16
    Activations Density 18.682%

    No Known Activations