© 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. 25791
    Prev
    Next
    INDEX
    Explanations

    references to amplifiers and amplification in the context of audio equipment

    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
    +0.16
    0.7%
    465
    +0.10
    0.5%
    328
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.16
    0.01
    343
    +0.10
    0.01
    690
    +0.10
    0.01
    Negative Logits
    SHIP
    -0.97
    naire
    -0.69
     Borders
    -0.68
    WHERE
    -0.66
     Cannes
    -0.65
     Kers
    -0.64
     Norm
    -0.64
     Roe
    -0.64
     Purg
    -0.64
     Cald
    -0.62
    POSITIVE LOGITS
    hetamine
    1.81
    het
    1.23
    ulla
    1.16
    ule
    1.09
    ute
    1.07
    ules
    1.05
    osite
    1.01
    onte
    0.97
    ension
    0.96
    olin
    0.96
    Activations Density 0.004%

    No Known Activations