© 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 49152
    9. 8-RES_FS49152-JB
    11. 45729
    Prev
    Next
    INDEX
    Explanations

    elements related to a schedule or organizational structure in a competitive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    544
    +0.10
    0.5%
    477
    +0.09
    0.4%
    244
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.10
    0.03
    640
    +0.09
    0.03
    93
    +0.09
    0.02
    Negative Logits
     enthusi
    -0.83
     unsus
    -0.71
     eaves
    -0.71
     constitu
    -0.70
     skelet
    -0.67
     elim
    -0.66
     barg
    -0.65
     speculation
    -0.64
     therap
    -0.64
     lawy
    -0.63
    POSITIVE LOGITS
    ãĥĺãĥ©
    0.89
    ļé
    0.84
     Wee
    0.75
    İĭ
    0.73
     Plain
    0.73
    Reviewer
    0.72
     Roller
    0.72
     Slug
    0.71
     Tycoon
    0.70
    shapeshifter
    0.68
    Activations Density 0.084%

    No Known Activations