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 3072
    5. 8-RES_FS3072-JB
    6. 579
    Prev
    Next
    INDEX
    Explanations

    names of specific entities or figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    362
    +0.14
    0.7%
    393
    +0.12
    0.6%
    145
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.14
    0.07
    572
    +0.12
    0.07
    362
    +0.11
    0.07
    Negative Logits
     beware
    -0.77
     patiently
    -0.71
     aloud
    -0.70
     forcefully
    -0.69
     delivered
    -0.69
     partake
    -0.69
    thood
    -0.69
     stopping
    -0.67
     recite
    -0.66
    perse
    -0.66
    POSITIVE LOGITS
    oret
    1.28
    atre
    1.24
    odor
    1.19
     Hague
    1.17
    resa
    1.14
    orem
    1.09
     Economist
    1.06
     Simpsons
    1.06
    odore
    1.03
     Guardian
    1.02
    Activations Density 0.463%

    No Known Activations