© 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. 41560
    Prev
    Next
    INDEX
    Explanations

    words related to claims and citations in discussions or reports

    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
    481
    +0.19
    0.9%
    74
    +0.12
    0.5%
    430
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.19
    0.04
    679
    +0.12
    0.05
    452
    +0.11
    0.03
    Negative Logits
    natureconservancy
    -0.76
     welf
    -0.71
     goodbye
    -0.70
     toast
    -0.69
    animate
    -0.68
     Himself
    -0.67
     dearly
    -0.67
     afar
    -0.66
    eering
    -0.63
    âĻ¥
    -0.62
    POSITIVE LOGITS
     detailing
    1.12
     titled
    1.12
    uggest
    1.05
     outlines
    1.03
     headlined
    1.01
     outlining
    0.94
    itled
    0.93
     entitled
    0.90
     dated
    0.88
     purported
    0.87
    Activations Density 0.251%

    No Known Activations