© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 15979
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of small or young children

    oai_token-act-pair · gpt-3.5-turbo

    references to young children, particularly focusing on the word "little."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igham
    -0.74
    idents
    -0.74
    iership
    -0.72
    chwitz
    -0.72
     largeDownload
    -0.71
    ontent
    -0.71
    iris
    -0.69
    lation
    -0.69
    Solution
    -0.67
    ï¸
    -0.67
    POSITIVE LOGITS
     girl
    0.98
     bit
    0.98
     boy
    0.95
     brother
    0.89
     boys
    0.88
     girls
    0.88
     kid
    0.85
     sister
    0.84
     snippets
    0.81
     guy
    0.81
    Activations Density 0.034%

    No Known Activations