© 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. 4045
    Prev
    Next
    INDEX
    Explanations

    descriptions and details about criminal activities reported by the police

    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
    105
    +0.13
    0.6%
    265
    +0.10
    0.5%
    723
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    723
    +0.13
    0.04
    105
    +0.10
    0.04
    333
    +0.10
    0.03
    Negative Logits
     contrace
    -0.89
    Downloadha
    -0.77
     subord
    -0.73
     filib
    -0.73
    Äĵ
    -0.72
    ãģ£
    -0.69
     tits
    -0.69
    Interstitial
    -0.68
     admired
    -0.67
    éģ
    -0.67
    POSITIVE LOGITS
     suspects
    1.13
    Investigators
    1.03
     detectives
    1.03
     Investigators
    1.00
     probable
    1.00
     suspect
    1.00
     investigators
    0.94
     motive
    0.94
    arnaev
    0.92
     suspected
    0.89
    Activations Density 0.388%

    No Known Activations