© 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. 37603
    Prev
    Next
    INDEX
    Explanations

    core concepts related to media production and historical context

    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
    373
    +0.13
    0.6%
    414
    +0.10
    0.5%
    501
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.13
    0.03
    153
    +0.10
    0.02
    155
    +0.09
    0.03
    Negative Logits
     Shroud
    -0.72
    ĸļ
    -0.70
    endum
    -0.68
     Conc
    -0.67
     Warrant
    -0.66
     Peel
    -0.66
     Pound
    -0.64
     Chow
    -0.64
    Dur
    -0.63
    ©¶æ
    -0.61
    POSITIVE LOGITS
    assets
    0.69
    lems
    0.68
    arts
    0.68
    erg
    0.67
    %);
    0.67
    ANS
    0.65
    ients
    0.64
    inem
    0.63
    imens
    0.63
    irds
    0.62
    Activations Density 0.044%

    No Known Activations