© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 12742
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, regulations, and policies

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" indicating connections or relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Deal
    -0.76
    ADVERTISEMENT
    -0.75
    æĥ
    -0.73
    ļéĨĴ
    -0.71
    =]
    -0.70
    .*
    -0.70
    Els
    -0.69
    :(
    -0.69
    î
    -0.68
    WATCH
    -0.68
    POSITIVE LOGITS
     therefore
    0.95
    rogen
    0.85
     consequently
    0.84
    romeda
    0.83
     vice
    0.82
    rogens
    0.78
     then
    0.78
     thus
    0.77
     strives
    0.71
    hester
    0.71
    Activations Density 0.909%

    No Known Activations