© 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. 16879
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and convictions

    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
    7
    +0.16
    0.7%
    665
    +0.14
    0.6%
    146
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.16
    0.02
    7
    +0.14
    0.02
    386
    +0.10
    0.02
    Negative Logits
    rosso
    -0.78
    yip
    -0.72
    walker
    -0.70
    andel
    -0.68
    dri
    -0.64
    rouse
    -0.64
    thora
    -0.64
    otin
    -0.63
    ija
    -0.63
    erd
    -0.62
    POSITIVE LOGITS
    icts
    1.16
     sentencing
    1.03
     sentenced
    0.93
     harshly
    0.91
     probation
    0.90
    encing
    0.89
    istrates
    0.88
     verdict
    0.86
     sentences
    0.84
     punishments
    0.81
    Activations Density 0.024%

    No Known Activations