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 49152
    5. 8-RES_FS49152-JB
    6. 40045
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial implications and resource allocation

    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
    392
    +0.12
    0.5%
    333
    +0.11
    0.5%
    442
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.12
    0.05
    655
    +0.11
    0.04
    283
    +0.11
    0.02
    Negative Logits
    anka
    -0.70
    ¬¼
    -0.70
    escription
    -0.68
    ctuary
    -0.65
     pione
    -0.64
    ature
    -0.64
    perty
    -0.64
    alach
    -0.63
    stros
    -0.62
    andestine
    -0.62
    POSITIVE LOGITS
    than
    1.42
     fewer
    1.38
     quicker
    1.38
     faster
    1.29
     slower
    1.27
     less
    1.22
     clearer
    1.22
     healthier
    1.22
     nicer
    1.20
     better
    1.20
    Activations Density 0.349%

    No Known Activations