© 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 EvalsExportsAPI 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. 7806
    Prev
    Next
    INDEX
    Explanations

    words related to manners and behavior towards others

    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
    572
    +0.10
    0.5%
    344
    +0.09
    0.4%
    633
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.10
    0.04
    261
    +0.09
    0.03
    646
    +0.09
    0.03
    Negative Logits
     GOODMAN
    -0.86
     disproportion
    -0.73
    arnaev
    -0.73
    senal
    -0.69
    VL
    -0.68
    ilion
    -0.68
     Layer
    -0.66
    Offline
    -0.66
    idem
    -0.64
    LR
    -0.64
    POSITIVE LOGITS
     embraced
    0.86
     entertained
    0.84
     parted
    0.84
     greeted
    0.83
     awaiting
    0.83
     inquired
    0.82
     awaited
    0.82
     welcomed
    0.81
     complied
    0.81
     accepted
    0.80
    Activations Density 0.073%

    No Known Activations