© 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. 41476
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and business solutions

    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
    447
    +0.13
    0.6%
    575
    +0.10
    0.5%
    697
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.13
    0.04
    232
    +0.10
    0.03
    210
    +0.09
    0.03
    Negative Logits
    aples
    -0.72
    =\"
    -0.68
     hurd
    -0.68
     asleep
    -0.66
     muted
    -0.65
     cozy
    -0.64
     hinge
    -0.64
     flee
    -0.64
     inclined
    -0.63
     cruelty
    -0.63
    POSITIVE LOGITS
    *.
    0.90
     Reloaded
    0.87
     Syndrome
    0.83
     Revis
    0.77
    _.
    0.77
    }.
    0.76
    *,
    0.75
    ®
    0.75
    ®,
    0.74
    TM
    0.73
    Activations Density 0.210%

    No Known Activations