© 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. 4-RES-JB
    11. 17086
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly the name "Marty."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific people, particularly those named Marty

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

    No Comments

    Negative Logits
    otin
    -0.91
    edIn
    -0.90
    hips
    -0.82
    umber
    -0.80
    ciating
    -0.80
    apo
    -0.78
    erness
    -0.77
    ularity
    -0.75
    xual
    -0.74
    tnc
    -0.74
    POSITIVE LOGITS
     Marty
    1.03
     Walsh
    0.81
     Feldman
    0.77
     Cah
    0.76
     McMahon
    0.74
     Cumm
    0.74
     Goldberg
    0.72
     Baird
    0.71
     Robbins
    0.70
     Decker
    0.69
    Activations Density 0.019%

    No Known Activations