Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1990
    Prev
    Next
    INDEX
    Explanations

    terms related to women's issues and rights

    oai_token-act-pair · gpt-3.5-turbo

    references to women and women's issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eme
    -0.83
    REDACTED
    -0.83
    ebus
    -0.79
    raltar
    -0.76
    anoia
    -0.74
    akespe
    -0.74
    opher
    -0.73
    pps
    -0.71
    adelphia
    -0.70
    EMA
    -0.70
    POSITIVE LOGITS
    folk
    1.19
     genital
    1.07
     empowerment
    1.05
    opausal
    1.04
     reproductive
    0.95
     genitals
    0.93
     menstru
    0.90
     entrepreneurs
    0.89
     breasts
    0.86
    hood
    0.86
    Activations Density 0.079%

    No Known Activations