© 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. 7921
    Prev
    Next
    INDEX
    Explanations

    descriptions of new projects or initiatives

    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
    36
    +0.26
    1.3%
    447
    +0.15
    0.7%
    393
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.26
    0.14
    250
    +0.15
    0.07
    636
    +0.13
    0.07
    Negative Logits
    iev
    -0.81
    anism
    -0.79
    enance
    -0.78
    words
    -0.74
    agree
    -0.71
    ache
    -0.67
    hes
    -0.67
    ees
    -0.67
    eny
    -0.65
    unknown
    -0.65
    POSITIVE LOGITS
     slew
    1.14
     plethora
    1.09
     bunch
    1.04
     raft
    1.03
     series
    1.02
     new
    1.01
     handful
    1.00
     multitude
    0.95
     variety
    0.94
     lot
    0.94
    Activations Density 0.311%

    No Known Activations