© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 379
    Prev
    Next
    INDEX
    Explanations

    information related to project phases and schedules

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    447
    +0.16
    0.7%
    517
    +0.13
    0.6%
    594
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    594
    +0.16
    0.04
    24
    +0.13
    0.04
    388
    +0.09
    0.04
    Negative Logits
    atan
    -0.66
    erc
    -0.64
    ocial
    -0.64
    piring
    -0.64
    amina
    -0.63
    athered
    -0.63
    mosp
    -0.62
    license
    -0.61
    aying
    -0.60
    arus
    -0.60
    POSITIVE LOGITS
     onwards
    0.99
     onward
    0.87
     Decision
    0.66
     Redux
    0.64
    +,
    0.62
    ITIES
    0.62
    Dialogue
    0.62
     Premiere
    0.62
    +.
    0.61
     Fin
    0.61
    Activations Density 0.188%

    No Known Activations