© 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. 1708
    Prev
    Next
    INDEX
    Explanations

    sports-related statistics, such as player performance and averages

    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
    176
    +0.11
    0.5%
    497
    +0.10
    0.5%
    23
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.11
    0.02
    512
    +0.10
    0.03
    303
    +0.09
    0.03
    Negative Logits
     presenter
    -0.69
     clo
    -0.65
     advis
    -0.64
     nesting
    -0.62
     colourful
    -0.62
     exclus
    -0.62
     encl
    -0.61
     worsh
    -0.60
     menus
    -0.60
     servicing
    -0.60
    POSITIVE LOGITS
    5
    1.05
    0
    1.01
    8
    0.98
    06
    0.96
    9
    0.96
    6
    0.94
    56
    0.93
    96
    0.93
    98
    0.91
    7
    0.90
    Activations Density 0.057%

    No Known Activations