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. 8-RES-JB
    6. 19874
    Prev
    Next
    INDEX
    Explanations

    phrases where a female subject is the main focus

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "she."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.84
    emetery
    -0.71
    vernment
    -0.70
    antage
    -0.69
    undo
    -0.68
    hovah
    -0.65
    ypes
    -0.64
     Observatory
    -0.64
    PDATE
    -0.63
    odder
    -0.63
    POSITIVE LOGITS
     herself
    1.54
    pher
    1.46
    athed
    1.29
    athing
    1.23
    pard
    1.20
    ffield
    1.10
    pherd
    1.10
    ikh
    1.03
    lled
    1.02
    ppard
    0.99
    Activations Density 0.127%

    No Known Activations