© 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. 7823
    Prev
    Next
    INDEX
    Explanations

    information related to public health issues, specifically focusing on preventing unwanted pregnancies and the risks associated with flooding and chemicals

    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
    373
    +0.18
    0.9%
    430
    +0.10
    0.5%
    214
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    576
    +0.18
    0.03
    684
    +0.10
    0.03
    181
    +0.10
    0.04
    Negative Logits
    ©¶æ
    -0.63
     Haitian
    -0.59
     eleph
    -0.59
     exting
    -0.56
    odder
    -0.55
     Hond
    -0.55
    ©¶æ¥µ
    -0.54
     hob
    -0.54
     Witches
    -0.54
     Greenwood
    -0.53
    POSITIVE LOGITS
    vati
    0.66
     âĸº
    0.64
     Flavoring
    0.60
    library
    0.60
    oad
    0.60
    Reviewer
    0.60
    VK
    0.59
    ivan
    0.59
    iv
    0.58
    abeth
    0.58
    Activations Density 0.144%

    No Known Activations