© 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. 2365
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals named Stephen

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Stephen"

    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
    eer
    -1.02
    eers
    -0.74
    mented
    -0.70
    ered
    -0.68
    ering
    -0.67
    footed
    -0.67
    ilion
    -0.65
    LOAD
    -0.64
    MENTS
    -0.63
    aukee
    -0.62
    POSITIVE LOGITS
     Hawking
    1.33
     Colbert
    1.07
     Paddock
    1.00
     Fry
    0.90
    sonian
    0.89
     Harper
    0.87
     Curry
    0.85
     Cove
    0.82
     Shank
    0.80
     Schwar
    0.79
    Activations Density 0.026%

    No Known Activations