© 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 12288
    9. 8-RES_FS12288-JB
    11. 1577
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and human rights violations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    447
    +0.18
    0.9%
    679
    +0.18
    0.8%
    640
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.18
    0.13
    6
    +0.18
    0.13
    440
    +0.10
    0.10
    Negative Logits
     satisf
    -0.74
     maniac
    -0.70
    ency
    -0.70
     deity
    -0.69
     unbeat
    -0.69
     ogre
    -0.67
     meaningless
    -0.66
     madness
    -0.65
    emort
    -0.65
    vind
    -0.65
    POSITIVE LOGITS
     According
    1.34
     Whereas
    1.32
     Earlier
    1.31
     Though
    1.17
     Particularly
    1.16
     While
    1.15
     Indeed
    1.14
     Recently
    1.13
     Specifically
    1.13
     Firstly
    1.13
    Activations Density 0.702%

    No Known Activations