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. 46037
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational roles and individuals in various contexts

    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
    +0.10
    0.4%
    357
    +0.10
    0.4%
    428
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.10
    0.04
    146
    +0.10
    0.04
    15
    +0.09
    0.04
    Negative Logits
    etheless
    -0.74
    enders
    -0.69
    ends
    -0.68
    inventoryQuantity
    -0.66
    uts
    -0.65
    norm
    -0.65
    ":"","
    -0.63
     Causes
    -0.63
     Period
    -0.62
     Increases
    -0.61
    POSITIVE LOGITS
     hooked
    0.94
     ready
    0.91
     attached
    0.84
     buzzing
    0.84
     handy
    0.83
     footing
    0.82
     stepping
    0.82
     installed
    0.82
     onboard
    0.81
     hanging
    0.81
    Activations Density 0.256%

    No Known Activations