© 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. 45567
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate clarity or lack thereof

    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
    388
    +0.11
    0.5%
    459
    +0.10
    0.5%
    240
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.11
    0.03
    242
    +0.10
    0.02
    388
    +0.10
    0.02
    Negative Logits
     tremend
    -0.86
    inse
    -0.84
     Loft
    -0.74
    uld
    -0.73
    ITAL
    -0.71
     arrog
    -0.69
     destro
    -0.67
    andom
    -0.67
     nostalg
    -0.66
    eries
    -0.65
    POSITIVE LOGITS
    ances
    1.23
    cut
    1.16
    headed
    1.00
    cuts
    0.93
    cutting
    0.90
    ance
    0.89
     indication
    0.84
     sailing
    0.84
    iary
    0.82
    faced
    0.80
    Activations Density 0.024%

    No Known Activations