© 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. 9-RES-JB
    11. 18281
    Prev
    Next
    INDEX
    Explanations

    proper nouns of famous personalities and organizations

    oai_token-act-pair · gpt-3.5-turbo

    colons and punctuation typically associated with headlines or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wana
    -0.86
    rawdownloadcloneembedreportprint
    -0.74
    æ©
    -0.72
    aband
    -0.64
    NetMessage
    -0.62
    represented
    -0.60
     prey
    -0.58
     populated
    -0.57
     packed
    -0.57
    undai
    -0.57
    POSITIVE LOGITS
     '[
    0.94
     Why
    0.92
     Doesn
    0.87
     "'
    0.85
     Didn
    0.84
     '
    0.84
     Beware
    0.83
     Saying
    0.83
     Would
    0.82
     Wrong
    0.82
    Activations Density 0.068%

    No Known Activations