© 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 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. 10383
    Prev
    Next
    INDEX
    Explanations

    information related to Blu-ray releases and editions

    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
    525
    +0.12
    0.5%
    537
    +0.10
    0.5%
    521
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.12
    0.02
    525
    +0.10
    0.02
    639
    +0.09
    0.02
    Negative Logits
    ETHOD
    -0.74
     TODAY
    -0.70
     SERV
    -0.69
     Shutterstock
    -0.68
     BASE
    -0.68
     disturbance
    -0.66
    llah
    -0.66
     Gallup
    -0.65
    atican
    -0.65
     idiosyncr
    -0.64
    POSITIVE LOGITS
    ray
    1.25
    Ray
    1.02
    rays
    0.97
    sided
    0.91
    eared
    0.88
    eye
    0.88
    nova
    0.87
    series
    0.83
    ops
    0.81
    cert
    0.80
    Activations Density 0.034%

    No Known Activations