Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16971
    Prev
    Next
    INDEX
    Explanations

    phrases related to pursuit or protection of a female character

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific female character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Female Descriptors

    No Comments

    Negative Logits
    ype
    -1.01
    ypes
    -0.91
    arios
    -0.80
    ornia
    -0.74
    inventoryQuantity
    -0.69
    anamo
    -0.68
    Ĥª
    -0.67
    atory
    -0.67
    acks
    -0.67
    eways
    -0.65
    POSITIVE LOGITS
     husband
    1.47
     daughter
    1.33
     granddaughter
    1.27
     niece
    1.26
     boyfriend
    1.26
     sister
    1.18
     breasts
    1.17
     daughters
    1.11
     vagina
    1.11
     fiance
    1.10
    Activations Density 0.091%

    No Known Activations