© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3430
    Prev
    Next
    INDEX
    Explanations

    mentions of or pertaining to transgender people

    oai_token-act-pair · gpt-3.5-turbo

    references to transgender and LGBTQ+ individuals and their related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aic
    -0.82
    Nut
    -0.80
    inventoryQuantity
    -0.76
    quickShipAvailable
    -0.75
    othy
    -0.73
    Recipe
    -0.68
    Autom
    -0.68
    HL
    -0.67
    Beer
    -0.67
    Software
    -0.66
    POSITIVE LOGITS
     disproportionately
    0.96
     residing
    0.93
     oppressed
    0.93
     living
    0.92
     marginalized
    0.92
     who
    0.90
    hood
    0.90
     queer
    0.88
     disproportion
    0.87
     persecuted
    0.86
    Activations Density 0.239%

    No Known Activations