© 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 12288
    9. 8-RES_FS12288-JB
    11. 1254
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical strength training and weightlifting

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    301
    +0.11
    0.5%
    212
    +0.10
    0.5%
    642
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    212
    +0.11
    0.01
    301
    +0.10
    0.01
    468
    +0.10
    0.01
    Negative Logits
     Palin
    -0.72
    TAG
    -0.64
    Cola
    -0.63
    sg
    -0.62
    tex
    -0.62
    ño
    -0.61
    errilla
    -0.60
    915
    -0.60
     Xiang
    -0.59
    keeper
    -0.59
    POSITIVE LOGITS
     weights
    1.13
    lift
    0.93
     lifting
    0.89
     lift
    0.89
     lifted
    0.84
    weight
    0.81
    igious
    0.80
     embargo
    0.78
    dogs
    0.77
     up
    0.75
    Activations Density 0.055%

    No Known Activations