© 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. 19526
    Prev
    Next
    INDEX
    Explanations

    debates or discussions surrounding political or controversial topics

    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
    373
    +0.12
    0.6%
    90
    +0.10
    0.5%
    520
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    572
    +0.12
    0.04
    45
    +0.10
    0.03
    212
    +0.09
    0.03
    Negative Logits
    culosis
    -0.74
     Exchange
    -0.68
    acket
    -0.66
    esa
    -0.65
    moil
    -0.64
    otonin
    -0.63
    Newsletter
    -0.63
    rehend
    -0.63
    ourse
    -0.60
    uates
    -0.60
    POSITIVE LOGITS
    cause
    0.98
     ya
    0.87
     huh
    0.82
     eh
    0.69
     sir
    0.69
    especially
    0.69
    pecially
    0.69
     congr
    0.67
    JV
    0.66
    laughs
    0.65
    Activations Density 0.233%

    No Known Activations