© 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. 45455
    Prev
    Next
    INDEX
    Explanations

    names or references to individuals, particularly those in positions of authority or recognition

    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
    26
    +0.09
    0.4%
    357
    +0.09
    0.4%
    503
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.09
    0.01
    11
    +0.09
    0.01
    232
    +0.09
    0.01
    Negative Logits
    terday
    -0.71
     Admir
    -0.69
    chnology
    -0.68
     IST
    -0.65
     aboriginal
    -0.64
     Commodore
    -0.63
    isance
    -0.60
     whales
    -0.60
     TODAY
    -0.60
     underwater
    -0.59
    POSITIVE LOGITS
    bons
    1.02
    bles
    1.00
    bled
    1.00
    endum
    0.99
    bling
    0.98
    bage
    0.97
    bent
    0.95
    bett
    0.93
    shaw
    0.92
    bler
    0.90
    Activations Density 0.002%

    No Known Activations