© 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. 3-RES-JB
    11. 12703
    Prev
    Next
    INDEX
    Explanations

    references to disabilities and related issues

    oai_token-act-pair · gpt-3.5-turbo

    references to disabilities and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ellipt
    -0.80
    hunt
    -0.74
    orically
    -0.72
    anza
    -0.70
    kaya
    -0.70
    ectar
    -0.69
    achus
    -0.68
    furt
    -0.68
    atorial
    -0.67
    rams
    -0.67
    POSITIVE LOGITS
     disabilities
    1.11
     disability
    1.09
     Disability
    1.02
     Disabled
    0.89
     impair
    0.81
     Discrimination
    0.78
    abled
    0.77
     inval
    0.76
     disabled
    0.75
     impairment
    0.71
    Activations Density 0.016%

    No Known Activations