© 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. 8-RES-JB
    11. 4920
    Prev
    Next
    INDEX
    Explanations

    references to contraceptives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to contraception and reproductive health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -1.23
    escription
    -0.90
    ĪĴ
    -0.84
    osta
    -0.81
    arnaev
    -0.78
    IELD
    -0.78
    cedented
    -0.77
    hov
    -0.75
    raq
    -0.74
    emort
    -0.72
    POSITIVE LOGITS
     pills
    1.13
     contraceptive
    1.11
     condoms
    1.05
     contraceptives
    1.04
     contraception
    0.97
     prescriptions
    0.88
     pregnancy
    0.88
     implant
    0.87
     condom
    0.87
     hormones
    0.86
    Activations Density 0.035%

    No Known Activations