© 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. 11-RES-JB
    11. 20506
    Prev
    Next
    INDEX
    Explanations

    references to sports games and match outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifies
    -0.70
    abuse
    -0.69
    scape
    -0.67
    olicy
    -0.67
    âĢİ
    -0.66
    ographers
    -0.62
    Reason
    -0.62
    =""
    -0.61
    forces
    -0.61
    oldemort
    -0.60
    POSITIVE LOGITS
     semifinals
    1.04
     midst
    1.02
     finals
    0.93
     meantime
    0.90
    ĸļ
    0.88
     aftermath
    0.88
     inaugural
    0.85
     Bahamas
    0.82
     rematch
    0.80
     standings
    0.79
    Activations Density 0.113%

    No Known Activations