© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 2858
    Prev
    Next
    INDEX
    Explanations

    Proper nouns or names in lists of items

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters and entities

    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
    rawdownloadcloneembedreportprint
    -0.85
     confir
    -0.76
    stocks
    -0.72
    agine
    -0.70
    :[
    -0.66
    Apr
    -0.65
    :/
    -0.64
     notor
    -0.61
    avascript
    -0.59
    stock
    -0.59
    POSITIVE LOGITS
    ADVERTISEMENT
    0.81
    ifacts
    0.63
    ridor
    0.60
    FORE
    0.59
    aque
    0.57
    FINEST
    0.57
    igers
    0.57
    raits
    0.54
     ._
    0.54
     Pax
    0.54
    Activations Density 0.209%

    No Known Activations