© 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 24576
    9. 8-RES_FS24576-JB
    11. 12056
    Prev
    Next
    INDEX
    Explanations

    4-letter words ending in 'um'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    309
    +0.16
    0.8%
    264
    +0.10
    0.5%
    399
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    482
    +0.16
    0.03
    81
    +0.10
    0.03
    232
    +0.10
    0.03
    Negative Logits
    omet
    -0.74
    ģ«
    -0.71
    ober
    -0.70
     232
    -0.69
    letal
    -0.68
    terday
    -0.67
    omical
    -0.67
    iff
    -0.67
     predec
    -0.66
    TPPStreamerBot
    -0.65
    POSITIVE LOGITS
    sg
    1.21
    S
    1.13
    sa
    1.05
    SR
    1.04
    sr
    1.03
    SA
    1.03
     Samp
    1.03
     Sak
    1.02
     Sa
    1.01
     Sv
    1.00
    Activations Density 0.174%

    No Known Activations