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. 41424
    Prev
    Next
    INDEX
    Explanations

    actions related to cutting and slicing

    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
    214
    +0.11
    0.5%
    723
    +0.10
    0.5%
    276
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.11
    0.02
    582
    +0.10
    0.02
    507
    +0.10
    0.02
    Negative Logits
    KY
    -0.80
     opio
    -0.78
    SPONSORED
    -0.77
     Moder
    -0.71
    Purchase
    -0.66
     Refresh
    -0.64
    BUS
    -0.64
    Story
    -0.63
    ammy
    -0.61
     Asylum
    -0.60
    POSITIVE LOGITS
    scene
    1.30
    aneous
    1.29
    lasses
    1.21
    scenes
    1.16
    ters
    1.14
    thro
    1.10
    lass
    1.05
    tin
    1.02
    tle
    1.02
    ting
    0.99
    Activations Density 0.014%

    No Known Activations