© 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
    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. 9460
    Prev
    Next
    INDEX
    Explanations

    phrases related to public health and social issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health and social issues

    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
    ebus
    -0.67
     fray
    -0.65
    =-=-
    -0.61
    adel
    -0.59
     stal
    -0.53
     Alley
    -0.53
     sorely
    -0.52
     relent
    -0.52
    emonium
    -0.51
    manship
    -0.51
    POSITIVE LOGITS
     contraceptive
    1.03
     contraception
    0.89
     antidepressants
    0.89
     breastfeeding
    0.86
     abortions
    0.85
     sexual
    0.85
     sexually
    0.85
     HIV
    0.84
     contraceptives
    0.83
     HPV
    0.82
    Activations Density 0.781%

    No Known Activations