© 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. 7017
    Prev
    Next
    INDEX
    Explanations

    phrases describing social or cultural perspectives related to specific groups of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to marginalized groups, particularly LGBTQ+ and Black individuals

    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
    Accessory
    -0.81
    Deal
    -0.74
    HL
    -0.73
    Nut
    -0.72
    quickShipAvailable
    -0.72
    FTWARE
    -0.72
     Inspection
    -0.70
    SET
    -0.67
    inventoryQuantity
    -0.67
    uner
    -0.66
    POSITIVE LOGITS
    hood
    0.94
     everywhere
    0.87
    paces
    0.82
     disproportionately
    0.81
     queer
    0.79
    folk
    0.78
     disproportion
    0.77
     patriarchy
    0.77
     oppressed
    0.74
     living
    0.74
    Activations Density 0.159%

    No Known Activations