© 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 1536
    9. 8-RES_FS1536-JB
    11. 1168
    Prev
    Next
    INDEX
    Explanations

    words related to energy technology and medical marijuana

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    314
    +0.23
    1.1%
    526
    +0.12
    0.6%
    7
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.23
    326
    +0.12
    0.18
    314
    +0.12
    -0.03
    Negative Logits
     reper
    -0.72
     Haram
    -0.63
     rink
    -0.59
     adv
    -0.58
     exha
    -0.55
     brim
    -0.55
     Nare
    -0.55
     crawl
    -0.55
     custody
    -0.54
     Peninsula
    -0.54
    POSITIVE LOGITS
    ing
    2.48
    ed
    2.05
    edIn
    1.68
    edly
    1.57
    ions
    1.56
    es
    1.52
    ively
    1.46
    ers
    1.43
    er
    1.42
    ment
    1.40
    Activations Density 4.907%

    No Known Activations