© 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. 11-RES-JB
    11. 22536
    Prev
    Next
    INDEX
    Explanations

    mentions of a female pronoun 'she'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word 'she' in various forms

    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
     constit
    -0.70
    ument
    -0.59
     iso
    -0.57
     Techn
    -0.57
     firsthand
    -0.56
     eleven
    -0.56
     Jr
    -0.56
     Circuit
    -0.55
     Yiannopoulos
    -0.55
    ANCE
    -0.55
    POSITIVE LOGITS
    pher
    1.62
    ffield
    1.51
    lled
    1.46
    ppard
    1.44
    pherd
    1.43
    pard
    1.42
    athed
    1.38
    ldon
    1.30
    ikh
    1.26
    athing
    1.25
    Activations Density 0.045%

    No Known Activations