© 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. 0-RES-JB
    11. 11908
    Prev
    Next
    INDEX
    Explanations

    instances of a specific pronoun 'she'

    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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     junk
    -0.59
     blink
    -0.58
     prop
    -0.57
     count
    -0.57
     serious
    -0.56
     third
    -0.55
     race
    -0.55
     fixed
    -0.54
     past
    -0.54
     chords
    -0.54
    POSITIVE LOGITS
    she
    4.29
    She
    2.06
     she
    1.70
     SHE
    1.63
     She
    1.59
    her
    1.34
    he
    1.32
    Her
    1.26
    they
    1.16
    shed
    1.07
    Activations Density 0.011%

    No Known Activations