© 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. 5589
    Prev
    Next
    INDEX
    Explanations

    instances of individuals being released from custody or detention

    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
    405
    +0.10
    0.4%
    147
    +0.10
    0.4%
    414
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.10
    0.02
    665
    +0.10
    0.02
    658
    +0.10
    0.02
    Negative Logits
    eries
    -0.65
     originals
    -0.59
    matic
    -0.58
    atomic
    -0.58
    igsaw
    -0.57
    gly
    -0.57
     Acquisition
    -0.56
     Mahjong
    -0.56
    iop
    -0.56
    nutrition
    -0.56
    POSITIVE LOGITS
     prisoners
    1.00
     prisoner
    1.00
     captives
    0.82
    oner
    0.81
     parole
    0.80
     detainees
    0.79
    quished
    0.78
     hostages
    0.76
    egu
    0.76
     pending
    0.75
    Activations Density 0.049%

    No Known Activations