© 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 12288
    9. 8-RES_FS12288-JB
    11. 1511
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to physical movements or actions

    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
    219
    +0.12
    0.5%
    639
    +0.10
    0.4%
    667
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    216
    +0.12
    0.06
    540
    +0.10
    0.07
    639
    +0.10
    0.05
    Negative Logits
    inately
    -0.73
    eva
    -0.73
    heric
    -0.72
    uate
    -0.72
    ses
    -0.71
    redo
    -0.71
    mented
    -0.71
    overe
    -0.70
    ieving
    -0.68
    omet
    -0.68
    POSITIVE LOGITS
     spree
    0.99
     mechanism
    0.93
     ability
    0.92
    redients
    0.91
    tons
    0.90
    rights
    0.80
     process
    0.78
     prowess
    0.77
     grounds
    0.74
     agent
    0.74
    Activations Density 0.458%

    No Known Activations