© 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. 1-RES-JB
    11. 14600
    Prev
    Next
    INDEX
    Explanations

    people's names, particularly the name "She"

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "She" indicating a female subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atory
    -0.74
     Skydragon
    -0.72
    displayText
    -0.71
    ilateral
    -0.67
    ugu
    -0.66
     Jimmy
    -0.63
     Jesse
    -0.62
    active
    -0.61
    folios
    -0.61
    kefeller
    -0.61
    POSITIVE LOGITS
    pherd
    1.23
    pher
    1.16
    pard
    1.13
    ffield
    1.05
    ppard
    1.03
    athing
    0.96
    athed
    0.94
    ldon
    0.93
     Majesty
    0.92
    affer
    0.90
    Activations Density 0.033%

    No Known Activations