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 6144
    5. 8-RES_FS6144-JB
    6. 4515
    Prev
    Next
    INDEX
    Explanations

    proper nouns, such as names of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    480
    +0.36
    1.7%
    127
    +0.10
    0.5%
    476
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.36
    0.11
    127
    +0.10
    0.07
    480
    +0.09
    0.00
    Negative Logits
     guiName
    -1.13
    etheless
    -0.80
     showc
    -0.54
    ãĢİ
    -0.52
     ."
    -0.52
    ãĢIJ
    -0.51
    foreseen
    -0.51
    ":[{"
    -0.51
    htaking
    -0.48
    wcs
    -0.48
    POSITIVE LOGITS
    )
    2.06
    )"
    1.97
    ),
    1.94
    ),"
    1.93
    ?)
    1.90
    )."
    1.86
    )",
    1.85
    )'
    1.84
    )?
    1.82
    ):
    1.82
    Activations Density 1.372%

    No Known Activations