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. 26030
    Prev
    Next
    INDEX
    Explanations

    references to specific commands and technical terms

    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
    87
    +0.41
    2.2%
    464
    +0.12
    0.7%
    127
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.41
    -0.01
    127
    +0.12
    0.04
    289
    +0.08
    0.01
    Negative Logits
     guiName
    -0.82
    etheless
    -0.55
    ãĢIJ
    -0.52
    wcs
    -0.50
    ãĢİ
    -0.48
     withd
    -0.43
     ."
    -0.42
    byss
    -0.41
    âķIJâķIJ
    -0.41
     ,"
    -0.40
    POSITIVE LOGITS
    )
    1.64
    )"
    1.61
    ),"
    1.56
    ?)
    1.55
    )."
    1.52
    ),
    1.51
    )'
    1.50
    )/
    1.49
    !)
    1.47
    *)
    1.46
    Activations Density 0.702%

    No Known Activations