© 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. 41528
    Prev
    Next
    INDEX
    Explanations

    references to privacy policies and user agreements

    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
    314
    +0.12
    0.6%
    125
    +0.10
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.12
    0.01
    477
    +0.10
    0.01
    306
    +0.10
    0.01
    Negative Logits
     guiName
    -0.72
    uable
    -0.63
    aughtered
    -0.62
     Rew
    -0.60
     sugg
    -0.60
     Brah
    -0.59
    pas
    -0.58
     Alph
    -0.58
     tert
    -0.57
    ovember
    -0.56
    POSITIVE LOGITS
    Privacy
    0.82
    ainment
    0.74
     sidebar
    0.67
    cookie
    0.64
     governing
    0.61
     Terms
    0.60
    orpor
    0.60
    VPN
    0.60
     Etsy
    0.59
    protect
    0.58
    Activations Density 0.018%

    No Known Activations