© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26624
    Prev
    Next
    INDEX
    Explanations

    terms related to figures, measurements, and forms

    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
    0.6%
    501
    +0.11
    0.5%
    643
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.02
    373
    +0.11
    -0.00
    530
    +0.09
    0.02
    Negative Logits
     stagnant
    -0.62
     jumper
    -0.60
     gorilla
    -0.59
     quar
    -0.59
    Constructed
    -0.58
     tightly
    -0.57
     Uran
    -0.56
     attendant
    -0.56
     universes
    -0.55
     nomine
    -0.55
    POSITIVE LOGITS
    hiba
    0.95
    oshenko
    0.87
    ush
    0.82
    aret
    0.78
    eless
    0.77
    ago
    0.77
    ias
    0.76
    oan
    0.75
    ogo
    0.75
    ronic
    0.74
    Activations Density 0.021%

    No Known Activations