© 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. 6313
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing opportunities and ensuring fairness and access to resources

    oai_token-act-pair · gpt-3.5-turbo

    themes related to social justice and equality

    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
     Tarant
    -0.71
     Starr
    -0.68
    ebus
    -0.64
    bot
    -0.63
     Cthulhu
    -0.63
     presided
    -0.61
    hot
    -0.61
     announcing
    -0.61
     Phantom
    -0.60
    atoon
    -0.60
    POSITIVE LOGITS
     accessing
    0.90
     empowerment
    0.87
     access
    0.87
     healthier
    0.84
     healthcare
    0.83
     enrichment
    0.79
     caregivers
    0.78
    utic
    0.78
     nutritious
    0.78
    rehensive
    0.77
    Activations Density 0.597%

    No Known Activations