© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24252
    Prev
    Next
    INDEX
    Explanations

    phrases related to gender, with a focus on females

    oai_token-act-pair · gpt-3.5-turbo

    references to the female gender

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

    No Comments

    Negative Logits
    rieg
    -0.86
    lov
    -0.85
    vous
    -0.79
    krit
    -0.78
    ozy
    -0.77
    ypes
    -0.76
    lay
    -0.75
    hemy
    -0.75
    weet
    -0.74
    akespe
    -0.74
    POSITIVE LOGITS
    volent
    1.25
     genital
    1.16
     empowerment
    1.01
     reproductive
    0.96
     genitals
    0.91
     infertility
    0.84
     menstrual
    0.83
     contraceptive
    0.82
     sexuality
    0.82
     female
    0.79
    Activations Density 0.022%

    No Known Activations