© 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. 12225
    Prev
    Next
    INDEX
    Explanations

    interrogative language

    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
    497
    +0.10
    0.5%
    687
    +0.10
    0.5%
    72
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.10
    0.04
    393
    +0.10
    0.05
    720
    +0.10
    0.04
    Negative Logits
     laure
    -0.77
    çīĪ
    -0.66
    ©¶æ
    -0.63
    tyard
    -0.60
    rique
    -0.59
    ¬¼
    -0.58
    roth
    -0.57
    scrib
    -0.57
     Corona
    -0.57
    roller
    -0.56
    POSITIVE LOGITS
     how
    1.26
     HOW
    1.16
     whether
    1.16
     WHY
    1.14
    why
    1.10
    how
    1.06
     why
    1.05
    whether
    1.05
     whereabouts
    1.01
     How
    0.91
    Activations Density 0.251%

    No Known Activations