© 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. 13719
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and rights

    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
    100
    +0.13
    0.6%
    268
    +0.10
    0.4%
    591
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.04
    575
    +0.10
    0.04
    146
    +0.09
    0.03
    Negative Logits
    nas
    -0.83
    gob
    -0.77
    rez
    -0.77
     Wand
    -0.75
    ERN
    -0.74
    jon
    -0.73
    DCS
    -0.73
    clips
    -0.72
    liest
    -0.72
    jack
    -0.71
    POSITIVE LOGITS
     protections
    1.24
     statute
    1.19
     laws
    1.17
     violation
    1.13
     statutes
    1.12
     exemption
    1.11
     clause
    1.11
     law
    1.07
     Amendment
    1.07
     litigation
    1.05
    Activations Density 0.133%

    No Known Activations