© 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. 45760
    Prev
    Next
    INDEX
    Explanations

    phrases and structures related to film or media titles

    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
    760
    +0.13
    0.6%
    493
    +0.12
    0.6%
    293
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    760
    +0.13
    0.03
    133
    +0.12
    0.03
    493
    +0.12
    0.02
    Negative Logits
     guiActive
    -0.76
     296
    -0.76
    ummer
    -0.75
    aline
    -0.75
    oni
    -0.73
    peria
    -0.72
     Pepper
    -0.71
    anners
    -0.71
    nan
    -0.70
    omon
    -0.70
    POSITIVE LOGITS
    س
    0.86
     Lash
    0.72
     Sag
    0.72
    08
    0.71
    adh
    0.69
     Sik
    0.67
    ==
    0.66
     Rw
    0.66
    WW
    0.66
    ت
    0.66
    Activations Density 0.068%

    No Known Activations