© 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 1536
    9. 8-RES_FS1536-JB
    11. 74
    Prev
    Next
    INDEX
    Explanations

    topics related to social and political issues, including justice, poverty, disease, nationality, religion, global events, governmental actions, and public policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    575
    +0.11
    0.5%
    711
    +0.10
    0.4%
    762
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.11
    0.26
    288
    +0.10
    0.27
    762
    +0.09
    0.24
    Negative Logits
    osite
    -0.56
     mature
    -0.55
    ameless
    -0.55
     specificity
    -0.52
     Hawks
    -0.52
     multip
    -0.51
    Clar
    -0.51
     gymn
    -0.51
     referen
    -0.51
     retract
    -0.51
    POSITIVE LOGITS
     respectively
    1.16
    ?,
    1.14
    .?
    1.13
    *.
    1.04
    ãĢĤ
    1.04
    .;
    1.00
    )?
    0.99
    )).
    0.99
     etc
    0.95
    }.
    0.94
    Activations Density 6.316%

    No Known Activations