© 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. 25813
    Prev
    Next
    INDEX
    Explanations

    references to fairy tales and related themes

    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
    288
    +0.13
    0.6%
    385
    +0.11
    0.5%
    737
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    737
    +0.11
    0.01
    620
    +0.10
    0.01
    Negative Logits
    aeda
    -0.87
    atility
    -0.82
    ebus
    -0.81
    ibaba
    -0.80
    upon
    -0.76
    iating
    -0.76
    inventoryQuantity
    -0.75
    isitions
    -0.74
    iferation
    -0.73
    artney
    -0.73
    POSITIVE LOGITS
    tale
    1.37
     tale
    1.25
     tales
    1.04
     Tale
    0.93
     fairy
    0.91
     princess
    0.87
    tailed
    0.80
    tail
    0.76
    lla
    0.74
     Tales
    0.73
    Activations Density 0.009%

    No Known Activations