© 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. 8-RES-JB
    11. 6824
    Prev
    Next
    INDEX
    Explanations

    words related to social justice movements and ideologies, particularly related to feminism and racism

    oai_token-act-pair · gpt-3.5-turbo

    concepts and discussions related to feminism, racism, and atheism

    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
     captcha
    -0.80
     deliveries
    -0.78
     Known
    -0.78
     delivery
    -0.75
     Cavern
    -0.73
     Landing
    -0.70
     HM
    -0.69
     Mast
    -0.69
     orally
    -0.69
     mast
    -0.68
    POSITIVE LOGITS
    ism
    1.40
    ophobic
    1.35
    ophob
    1.35
    eness
    1.34
    ophobia
    1.34
    atism
    1.27
    iosity
    1.21
    femin
    1.17
    acist
    1.17
    itism
    1.15
    Activations Density 0.144%

    No Known Activations