© 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 EvalsExportsinterp-engineNEWAPI 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. 2803
    Prev
    Next
    INDEX
    Explanations

    references to specific events or investigations involving authorities and legal matters

    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
    756
    +0.14
    0.6%
    584
    +0.11
    0.5%
    735
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.14
    0.07
    38
    +0.11
    0.05
    756
    +0.10
    -0.01
    Negative Logits
     Krypt
    -0.73
     Bub
    -0.67
    ONSORED
    -0.65
    Mega
    -0.64
    çķ
    -0.64
     neighbor
    -0.64
     neighbour
    -0.63
    onement
    -0.63
    TX
    -0.62
     Bolt
    -0.62
    POSITIVE LOGITS
     themselves
    1.00
     discretion
    0.98
     salaries
    0.98
     vested
    0.95
     oversee
    0.93
    ateurs
    0.87
     routinely
    0.86
    untled
    0.82
     desks
    0.80
     overseeing
    0.79
    Activations Density 0.642%

    No Known Activations