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 24576
    5. 8-RES_FS24576-JB
    6. 8203
    Prev
    Next
    INDEX
    Explanations

    words related to ice hockey players and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    436
    +0.13
    0.6%
    128
    +0.11
    0.5%
    734
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.03
    373
    +0.11
    -0.01
    406
    +0.10
    0.02
    Negative Logits
    ufact
    -0.67
     sled
    -0.64
     wiser
    -0.61
     wrestle
    -0.61
     compass
    -0.61
     warr
    -0.60
     disg
    -0.59
     trave
    -0.59
     Clover
    -0.59
     Yosemite
    -0.59
    POSITIVE LOGITS
    alion
    0.78
    rette
    0.78
    inary
    0.75
    ulent
    0.72
    neau
    0.72
    eless
    0.71
    rine
    0.70
    atro
    0.68
    atis
    0.67
    olated
    0.67
    Activations Density 0.087%

    No Known Activations