© 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. 2-RES-JB
    11. 23687
    Prev
    Next
    INDEX
    Explanations

    references to a specific demographic group

    oai_token-act-pair · gpt-3.5-turbo

    references to privilege associated with race

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mortg
    -0.76
     polls
    -0.73
     democratically
    -0.68
     filibuster
    -0.65
     mathemat
    -0.65
     tariff
    -0.63
     indu
    -0.62
     contrace
    -0.62
     widgets
    -0.62
     mortgages
    -0.61
    POSITIVE LOGITS
     msec
    0.76
    itans
    0.68
    interstitial
    0.67
    INGTON
    0.67
    YING
    0.67
    GoldMagikarp
    0.67
    toggle
    0.66
    cca
    0.66
    ornings
    0.65
    Spect
    0.64
    Activations Density 0.000%

    No Known Activations