© 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. 45502
    Prev
    Next
    INDEX
    Explanations

    references to evolutionary concepts related to species and their characteristics

    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
    7
    +0.12
    0.5%
    756
    +0.12
    0.5%
    664
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.12
    -0.01
    529
    +0.12
    0.03
    7
    +0.11
    0.03
    Negative Logits
    committee
    -0.82
     Transparency
    -0.80
     NCT
    -0.78
    Safety
    -0.78
    channelAvailability
    -0.74
    Counter
    -0.73
     blocker
    -0.72
    Recommend
    -0.72
    ebin
    -0.72
    Board
    -0.72
    POSITIVE LOGITS
     ancestors
    1.26
     civilizations
    1.20
     ancestor
    1.19
     prehistoric
    1.13
     proto
    1.12
     civilisation
    1.09
     extinct
    1.09
     millennia
    1.08
     Neander
    1.07
     Homo
    1.06
    Activations Density 0.300%

    No Known Activations