© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 42908
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of individuals and their qualities

    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
    279
    +0.11
    0.5%
    621
    +0.11
    0.5%
    628
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    628
    +0.11
    0.03
    122
    +0.11
    0.03
    284
    +0.10
    0.03
    Negative Logits
    odox
    -0.87
     lest
    -0.85
    ptives
    -0.84
    ensibly
    -0.81
    utterstock
    -0.80
    haps
    -0.77
    surprisingly
    -0.75
     ®
    -0.72
    ply
    -0.72
    ©¶æ
    -0.71
    POSITIVE LOGITS
     negotiator
    1.02
     compliment
    0.99
     job
    0.94
     accomplishment
    0.94
     asset
    0.90
     respect
    0.88
     opportunity
    0.87
     idea
    0.86
     example
    0.85
     organization
    0.85
    Activations Density 0.073%

    No Known Activations