© 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. 4-RES-JB
    11. 10920
    Prev
    Next
    INDEX
    Explanations

    words related to reproductive health and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to birth control and birth certificates

    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
    é¾
    -0.80
    âķIJ
    -0.78
    rez
    -0.77
    NRS
    -0.74
    Ni
    -0.72
    ngth
    -0.72
    Reviewer
    -0.72
    âĸ¬
    -0.72
    inational
    -0.71
     Cosponsors
    -0.70
    POSITIVE LOGITS
     womb
    0.97
     pills
    0.91
     implant
    0.78
     contraceptive
    0.77
     nurse
    0.76
     marathon
    0.73
     embryo
    0.73
     ultrasound
    0.73
     careg
    0.72
     vaccination
    0.70
    Activations Density 0.088%

    No Known Activations