© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9438
    Prev
    Next
    INDEX
    Explanations

    words related to opinions and sentiments, especially negative feelings or attitudes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    497
    +0.14
    0.6%
    278
    +0.13
    0.6%
    756
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.14
    0.05
    288
    +0.13
    0.06
    285
    +0.13
    0.04
    Negative Logits
    ITNESS
    -0.70
    akings
    -0.68
    CRE
    -0.64
    monary
    -0.64
    changes
    -0.63
    INC
    -0.63
     Farming
    -0.62
     Refresh
    -0.62
    uggest
    -0.62
    Pool
    -0.62
    POSITIVE LOGITS
     glare
    0.91
     toward
    0.88
     towards
    0.83
     levied
    0.82
     leveled
    0.77
     hated
    0.77
    uous
    0.77
     stares
    0.73
     Ferdinand
    0.72
     lash
    0.72
    Activations Density 0.386%

    No Known Activations