© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23923
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing up questions or reasons in discussions

    oai_token-act-pair · gpt-4o-miniTriggered 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
    274
    +0.11
    0.5%
    88
    +0.10
    0.5%
    715
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.03
    172
    +0.10
    0.02
    274
    +0.10
    0.02
    Negative Logits
     tolerated
    -0.67
     endors
    -0.65
     communicated
    -0.65
    estic
    -0.62
     assimil
    -0.60
    agos
    -0.59
     vetted
    -0.59
     outnumbered
    -0.59
    controlled
    -0.58
     streamed
    -0.58
    POSITIVE LOGITS
     Conclusion
    0.91
     wondering
    0.84
     conclude
    0.84
    amaz
    0.84
     conclusion
    0.83
     why
    0.82
    zsche
    0.81
     QUEST
    0.81
     concluding
    0.81
    =-=-=-=-
    0.79
    Activations Density 0.130%

    No Known Activations