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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2429
    Prev
    Next
    INDEX
    Explanations

    programming code and technical terms related to computer science

    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
    373
    +0.53
    6.6%
    87
    +0.52
    6.4%
    481
    +0.22
    2.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.53
    -0.04
    373
    +0.52
    -0.22
    756
    +0.22
    -0.14
    Negative Logits
    obyl
    -0.20
     Forums
    -0.19
     Belfast
    -0.19
     Âł
    -0.19
     Blockchain
    -0.18
    ↵Âł
    -0.18
     fixme
    -0.18
     ......
    -0.18
     alot
    -0.18
     ICO
    -0.18
    POSITIVE LOGITS
    swers
    0.19
    vice
    0.19
    ¿½
    0.19
    azard
    0.18
    ueless
    0.17
    urden
    0.17
    romptu
    0.17
    itably
    0.17
    ONSORED
    0.17
    ened
    0.17
    Activations Density 15.124%

    No Known Activations