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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19455
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports seasons and player performance

    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
    481
    +0.16
    0.7%
    277
    +0.10
    0.4%
    603
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    662
    +0.16
    0.04
    651
    +0.10
    0.04
    199
    +0.09
    0.04
    Negative Logits
    IBLE
    -0.70
    SPONSORED
    -0.68
     discretion
    -0.67
    Companies
    -0.66
    upon
    -0.63
    english
    -0.63
     practicable
    -0.63
     hereby
    -0.62
    Mods
    -0.62
     GOODMAN
    -0.61
    POSITIVE LOGITS
     stint
    1.16
     slump
    1.05
     hiatus
    1.04
     debacle
    1.01
     setbacks
    1.01
     breakup
    0.99
     disastrous
    0.97
     disappointing
    0.94
     setback
    0.93
     weekend
    0.92
    Activations Density 0.353%

    No Known Activations