© 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. 41540
    Prev
    Next
    INDEX
    Explanations

    numerical data related to Brexit and its associated political figures

    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
    274
    +0.11
    0.6%
    726
    +0.09
    0.4%
    135
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.11
    0.01
    373
    +0.09
    -0.00
    45
    +0.08
    0.00
    Negative Logits
    gall
    -0.64
    ht
    -0.62
    found
    -0.61
    chy
    -0.57
    chens
    -0.57
    ymm
    -0.55
    xs
    -0.54
    saf
    -0.54
    chet
    -0.53
    gest
    -0.53
    POSITIVE LOGITS
     respectively
    0.73
    ļéĨĴ
    0.67
    anwhile
    0.67
     commuting
    0.63
    independence
    0.62
    »Ĵ
    0.60
    soType
    0.60
    «ĺ
    0.57
    dayName
    0.56
     Emirates
    0.56
    Activations Density 0.005%

    No Known Activations