© 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. 45815
    Prev
    Next
    INDEX
    Explanations

    elements related to classifications and types, especially in contexts of data and statistics

    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
    27
    +0.14
    0.6%
    430
    +0.10
    0.5%
    123
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.14
    0.03
    288
    +0.10
    0.03
    258
    +0.10
    0.03
    Negative Logits
    ibaba
    -0.91
    endas
    -0.67
     Pengu
    -0.63
     targ
    -0.60
     belie
    -0.59
     tiss
    -0.58
     referen
    -0.57
     resil
    -0.57
     Unloaded
    -0.57
    vironments
    -0.57
    POSITIVE LOGITS
    loading
    0.78
    antine
    0.76
     guiActiveUn
    0.69
     decree
    0.68
     descending
    0.67
    heading
    0.66
    claw
    0.65
    umbers
    0.65
    ousing
    0.65
     alone
    0.65
    Activations Density 0.120%

    No Known Activations