© 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. 6-RES-JB
    11. 14450
    Prev
    Next
    INDEX
    Explanations

    mentions of a woman named "Ms" in specific contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals titled "Ms." in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appre
    -0.83
    sole
    -0.73
     brim
    -0.72
     destro
    -0.69
     tremend
    -0.67
    etheus
    -0.67
     acad
    -0.66
    ÃĥÃĤ
    -0.66
     sax
    -0.64
    */(
    -0.64
    POSITIVE LOGITS
    athed
    0.87
    ureen
    0.76
     Nina
    0.75
     Mary
    0.75
    anie
    0.72
     Claire
    0.72
    abel
    0.72
     Isabel
    0.71
     Lori
    0.71
     Nicole
    0.71
    Activations Density 0.015%

    No Known Activations