© 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. 7-RES-JB
    11. 19191
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with varying surnames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals, particularly with the title "Ms." followed by their names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tyr
    -0.80
     appre
    -0.79
     stewards
    -0.76
     enthusi
    -0.75
     skelet
    -0.74
     destro
    -0.73
    ÃĥÃĤ
    -0.71
    rawdownloadcloneembedreportprint
    -0.70
     eleph
    -0.70
    sole
    -0.69
    POSITIVE LOGITS
     Fiorina
    0.82
     Pelosi
    0.80
     Jill
    0.77
     Lynch
    0.72
     Olson
    0.72
     Pill
    0.72
     Hyde
    0.71
    channelAvailability
    0.71
     Jewel
    0.69
     Mae
    0.69
    Activations Density 0.015%

    No Known Activations