© 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. 41152
    Prev
    Next
    INDEX
    Explanations

    unique character symbols and foreign language characters

    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
    373
    +0.14
    0.7%
    228
    +0.13
    0.6%
    284
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.01
    406
    +0.13
    0.01
    50
    +0.10
    0.01
    Negative Logits
     equival
    -0.57
    eele
    -0.57
    pole
    -0.56
     eleph
    -0.55
     Penet
    -0.54
     satur
    -0.54
     locations
    -0.53
    gdala
    -0.53
     bonding
    -0.52
    cano
    -0.52
    POSITIVE LOGITS
    ħ
    1.08
    Ķ
    1.08
    ī
    1.06
    ĺ
    1.06
    Į
    1.03
    Ł
    1.02
    ľ
    1.00
    ı
    1.00
    ¿
    0.99
    ¼
    0.99
    Activations Density 0.007%

    No Known Activations