© 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. 17337
    Prev
    Next
    INDEX
    Explanations

    quoted statements made by someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported speech or quotations

    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
     Memor
    -0.62
    peat
    -0.61
    TABLE
    -0.60
    Tags
    -0.59
     Tradable
    -0.58
    ppings
    -0.57
    ãĥİ
    -0.55
    actly
    -0.55
     Scrib
    -0.55
     Written
    -0.55
    POSITIVE LOGITS
     sarcast
    0.87
     emphatically
    0.82
     diplom
    0.79
     bluntly
    0.78
     rhet
    0.72
     anecd
    0.72
     pointing
    0.70
     confidently
    0.69
     adding
    0.68
     persu
    0.66
    Activations Density 0.099%

    No Known Activations