© 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. 10-RES-JB
    11. 8585
    Prev
    Next
    INDEX
    Explanations

    pronouns 'her' and 'she'

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual and their experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ype
    -1.00
    ypes
    -0.99
    ornia
    -0.81
    kefeller
    -0.75
    VERTIS
    -0.71
    isco
    -0.71
    ollo
    -0.67
    arios
    -0.66
    flex
    -0.65
    undo
    -0.65
    POSITIVE LOGITS
     husband
    1.72
     boyfriend
    1.28
    metic
    1.27
    cule
    1.23
    ding
    1.22
     herself
    1.22
     daughter
    1.19
     vagina
    1.10
     maiden
    1.09
     granddaughter
    1.08
    Activations Density 0.122%

    No Known Activations