© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19781
    Prev
    Next
    INDEX
    Explanations

    technical terms related to capacity and capability in infrastructure or engineering contexts

    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
    288
    +0.14
    0.6%
    161
    +0.12
    0.5%
    678
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.01
    596
    +0.12
    0.01
    653
    +0.11
    0.01
    Negative Logits
    roma
    -0.81
    aida
    -0.80
    ĸļ
    -0.72
    gnu
    -0.70
    ochet
    -0.70
    bart
    -0.69
    lique
    -0.68
    scene
    -0.68
    cause
    -0.67
    rom
    -0.67
    POSITIVE LOGITS
     capacities
    1.40
     capacity
    1.32
     Capacity
    1.15
    capacity
    1.05
     utilization
    1.01
     capability
    0.81
     capabilities
    0.79
     overflow
    0.77
     mismatch
    0.77
     gaps
    0.76
    Activations Density 0.022%

    No Known Activations