© 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. 26662
    Prev
    Next
    INDEX
    Explanations

    phrases that denote precision or specificity in statements

    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
    540
    +0.11
    0.5%
    223
    +0.11
    0.5%
    43
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.11
    0.02
    223
    +0.11
    0.02
    43
    +0.10
    0.01
    Negative Logits
     Flavoring
    -0.70
    oké
    -0.70
    oscopic
    -0.69
    ngth
    -0.66
    rift
    -0.66
    cffff
    -0.64
    rug
    -0.64
    ocene
    -0.64
     sacrific
    -0.63
    itiz
    -0.62
    POSITIVE LOGITS
    ãĤ¨
    0.78
     opposite
    0.76
     wrong
    0.68
     why
    0.68
     analogous
    0.65
    minus
    0.64
     correct
    0.64
    µ
    0.61
     Horowitz
    0.61
    ¯
    0.61
    Activations Density 0.006%

    No Known Activations