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 49152
    5. 8-RES_FS49152-JB
    6. 26140
    Prev
    Next
    INDEX
    Explanations

    the word "long" as it relates to duration or distance

    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
    662
    +0.11
    0.5%
    130
    +0.10
    0.5%
    459
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.11
    0.04
    344
    +0.10
    0.04
    662
    +0.10
    0.03
    Negative Logits
     Thumbnails
    -0.74
    Mods
    -0.66
    illions
    -0.65
    rencies
    -0.64
    qqa
    -0.64
    packages
    -0.64
    oppers
    -0.64
    CB
    -0.63
    selves
    -0.62
     Territories
    -0.62
    POSITIVE LOGITS
    itudinal
    1.11
    sword
    1.10
    itud
    1.10
     overdue
    1.01
     ago
    0.99
    shore
    0.99
     awaited
    0.92
     term
    0.90
    lasting
    0.86
    itude
    0.86
    Activations Density 0.029%

    No Known Activations