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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 18751
    Prev
    Next
    INDEX
    Explanations

    words related to a specific female character named "her" or pronouns indicating her

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, suggesting focus on personal narratives or achievements

    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
    •female

    No Comments

    Negative Logits
    ypes
    -0.99
    ype
    -0.99
    ornia
    -0.82
    kefeller
    -0.78
    arios
    -0.75
    isco
    -0.69
    anamo
    -0.69
    ollo
    -0.69
    hovah
    -0.68
    undo
    -0.67
    POSITIVE LOGITS
     husband
    1.50
    ding
    1.32
    cule
    1.29
    metic
    1.25
     herself
    1.16
     boyfriend
    1.10
    ded
    1.09
    nia
    1.06
     daughter
    1.06
     Majesty
    1.04
    Activations Density 0.136%

    No Known Activations