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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 45563
    Prev
    Next
    INDEX
    Explanations

    phrases related to research and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.20
    0.9%
    622
    +0.09
    0.4%
    361
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    557
    +0.20
    0.03
    648
    +0.09
    0.03
    587
    +0.09
    0.03
    Negative Logits
    thing
    -0.68
    bered
    -0.67
    ometers
    -0.67
    amination
    -0.66
     comprom
    -0.66
    vous
    -0.64
    ringe
    -0.63
    ometer
    -0.62
    EST
    -0.62
    fax
    -0.62
    POSITIVE LOGITS
     Surv
    0.78
     Causes
    0.77
     topics
    0.70
     Courage
    0.70
     Strategies
    0.69
     Understanding
    0.67
     Lessons
    0.67
     Making
    0.67
     behalf
    0.66
     twentieth
    0.66
    Activations Density 0.097%

    No Known Activations