© 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 24576
    9. 8-RES_FS24576-JB
    11. 8152
    Prev
    Next
    INDEX
    Explanations

    words related to media and press

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    481
    +0.14
    0.6%
    447
    +0.13
    0.6%
    288
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.09
    628
    +0.13
    0.05
    325
    +0.10
    0.06
    Negative Logits
    edIn
    -0.80
    tein
    -0.77
    BuyableInstoreAndOnline
    -0.66
    Hop
    -0.66
    perse
    -0.66
    ļé
    -0.65
    Ô
    -0.65
    ¶æ
    -0.64
     Flavoring
    -0.63
    tions
    -0.62
    POSITIVE LOGITS
     itself
    1.06
    liest
    0.91
     microbiome
    0.86
    osphere
    0.84
    ousel
    0.76
    cients
    0.74
    iest
    0.70
     sphere
    0.69
     hierarchy
    0.69
     menace
    0.67
    Activations Density 0.399%

    No Known Activations