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. 5455
    Prev
    Next
    INDEX
    Explanations

    names of individuals or entities

    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
    87
    +0.23
    1.5%
    283
    +0.10
    0.6%
    756
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.23
    0.18
    659
    +0.10
    0.14
    314
    +0.10
    -0.01
    Negative Logits
     FANTASY
    -0.51
     archived
    -0.51
     carefully
    -0.50
    natureconservancy
    -0.50
     concise
    -0.50
     strategically
    -0.50
     cautiously
    -0.48
     offline
    -0.48
     anonymity
    -0.47
     digitally
    -0.47
    POSITIVE LOGITS
    $.
    0.59
    "],
    0.52
    ]).
    0.51
    ]."
    0.51
    ]),
    0.50
    ida
    0.50
    )).
    0.50
    .).
    0.49
    lad
    0.49
    alion
    0.49
    Activations Density 2.807%

    No Known Activations