© 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 49152
    9. 8-RES_FS49152-JB
    11. 24020
    Prev
    Next
    INDEX
    Explanations

    references to events and actions involving detainment and release

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    87
    +0.22
    1.1%
    464
    +0.15
    0.7%
    316
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.22
    0.04
    87
    +0.15
    -0.01
    464
    +0.10
    0.03
    Negative Logits
     largeDownload
    -0.81
    ãĤ¶
    -0.72
    £ı
    -0.71
    ccording
    -0.67
    ä½ľ
    -0.66
    ãĤ¨ãĥ«
    -0.64
    ||||
    -0.62
    ModLoader
    -0.62
    ×ŀ
    -0.61
    "))
    -0.60
    POSITIVE LOGITS
     Dou
    0.59
     NOTE
    0.58
     Plus
    0.57
     Featuring
    0.56
     Also
    0.56
     AU
    0.55
     Grav
    0.54
     Requires
    0.54
     Includes
    0.53
    }.
    0.53
    Activations Density 0.192%

    No Known Activations