© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14747
    Prev
    Next
    INDEX
    Explanations

    words related to technology and legislation

    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
    481
    +0.33
    1.5%
    288
    +0.10
    0.5%
    146
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.33
    0.07
    481
    +0.10
    0.06
    146
    +0.09
    0.04
    Negative Logits
     swat
    -0.63
    DERR
    -0.62
    arers
    -0.61
    loads
    -0.61
    ittees
    -0.60
    immers
    -0.60
    oppers
    -0.59
    akers
    -0.59
    omever
    -0.58
     sqor
    -0.57
    POSITIVE LOGITS
     titled
    0.73
     guiActiveUnfocused
    0.67
     wherein
    0.61
     called
    0.61
     discussed
    0.60
     playbook
    0.59
     entitled
    0.58
     comprising
    0.57
     Revised
    0.57
     Intermediate
    0.57
    Activations Density 0.461%

    No Known Activations