© 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. 7-RES-JB
    11. 8581
    Prev
    Next
    INDEX
    Explanations

    pronouns 'he' and 'she'

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly those referring to males and females

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Azerb
    -0.73
     Dres
    -0.68
     Buddy
    -0.65
     Argon
    -0.65
     Borders
    -0.63
     Jae
    -0.62
     Berk
    -0.62
    Category
    -0.62
     Royale
    -0.60
     Woodward
    -0.59
    POSITIVE LOGITS
    vernment
    0.79
    quickShipAvailable
    0.78
    amins
    0.77
    mos
    0.77
    Í
    0.76
    zbollah
    0.75
    rael
    0.74
    lder
    0.72
    pec
    0.71
    OSP
    0.70
    Activations Density 0.076%

    No Known Activations