© 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. 8-RES-JB
    11. 19268
    Prev
    Next
    INDEX
    Explanations

    names of people 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eer
    -1.11
     circ
    -0.74
    engers
    -0.72
    graded
    -0.72
    footed
    -0.71
    mented
    -0.70
     guiActiveUnfocused
    -0.69
    cffffcc
    -0.68
    hops
    -0.67
     balloon
    -0.65
    POSITIVE LOGITS
     Hawking
    1.32
     Paddock
    1.06
     Colbert
    1.04
    sonian
    0.96
     Fry
    0.92
     Stras
    0.91
    son
    0.91
    aceous
    0.88
     Harper
    0.83
     Curry
    0.82
    Activations Density 0.020%

    No Known Activations