© 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. 11-RES-JB
    11. 706
    Prev
    Next
    INDEX
    Explanations

    terms related to abortion

    oai_token-act-pair · gpt-3.5-turbo

    references to abortion and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -1.12
     Riy
    -0.74
     guiActiveUnfocused
    -0.74
    abulary
    -0.72
    auga
    -0.71
    auri
    -0.70
    inguished
    -0.70
    ffiti
    -0.68
    pora
    -0.68
    hew
    -0.67
    POSITIVE LOGITS
     clinics
    1.17
     clinic
    1.14
     pills
    1.00
     abortions
    1.00
     contraceptive
    1.00
    abortion
    0.98
     abortion
    0.97
     rights
    0.95
     provider
    0.93
     contraception
    0.93
    Activations Density 0.049%

    No Known Activations