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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12844
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to a female subject

    oai_token-act-pair · gpt-3.5-turbo

    occurrences 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 @ 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
    emetery
    -0.75
    kefeller
    -0.71
    odder
    -0.64
     srfAttach
    -0.63
     Skydragon
    -0.62
    Magikarp
    -0.61
    PDATE
    -0.61
    undo
    -0.60
    antage
    -0.59
     erection
    -0.59
    POSITIVE LOGITS
     herself
    1.71
    pher
    1.53
    athed
    1.35
    pard
    1.31
    athing
    1.22
    ffield
    1.19
    pherd
    1.18
    ikh
    1.13
    lled
    1.11
    ppard
    1.09
    Activations Density 0.131%

    No Known Activations