© 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. 1534
    Prev
    Next
    INDEX
    Explanations

    details in a narrative description related to a specific location

    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
    636
    +0.15
    0.7%
    421
    +0.11
    0.5%
    362
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.17
    636
    +0.11
    0.12
    124
    +0.10
    0.12
    Negative Logits
    onda
    -0.69
    ogg
    -0.67
    EStream
    -0.63
    SPONSORED
    -0.63
    REDACTED
    -0.62
    parser
    -0.62
    interstitial
    -0.61
    »Ĵ
    -0.60
    icians
    -0.59
    usa
    -0.59
    POSITIVE LOGITS
     fortunes
    0.97
     existing
    0.89
     reputation
    0.85
     entire
    0.84
     footprint
    0.84
     momentum
    0.83
     foothold
    0.81
     relationship
    0.81
     morale
    0.80
     defences
    0.79
    Activations Density 4.179%

    No Known Activations