© 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. 6535
    Prev
    Next
    INDEX
    Explanations

    descriptions of historical or fictional characters with notable achievements and qualities

    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
    36
    +0.29
    1.4%
    393
    +0.14
    0.7%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.29
    0.15
    328
    +0.14
    0.06
    250
    +0.11
    0.05
    Negative Logits
    ographs
    -0.79
    advertisement
    -0.77
    videos
    -0.77
    Edit
    -0.75
    edit
    -0.72
    advertising
    -0.72
    Arizona
    -0.70
    agues
    -0.70
    Xbox
    -0.70
    email
    -0.70
    POSITIVE LOGITS
     reminder
    1.22
     mixture
    1.14
     combination
    1.14
     glimpse
    1.10
     manifestation
    1.06
     willingness
    1.06
     reflection
    1.05
     gradual
    1.04
     tendency
    1.04
     testament
    1.03
    Activations Density 0.299%

    No Known Activations