© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 3087
    Prev
    Next
    INDEX
    Explanations

    phrases related to race and discrimination, particularly regarding racism and responses to it

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    statements criticizing racist behavior and incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dropbox
    -0.77
     Rao
    -0.73
     Chess
    -0.73
     Ars
    -0.70
     Wired
    -0.70
     envis
    -0.69
     Kindle
    -0.69
     opium
    -0.69
     repay
    -0.69
     Atari
    -0.68
    POSITIVE LOGITS
    DonaldTrump
    1.34
    ogyn
    1.13
     bigot
    1.13
    TRUMP
    1.10
    GOP
    1.09
     bigotry
    1.06
    Republican
    1.03
    racist
    1.03
     racist
    1.02
     racists
    1.01
    Activations Density 0.848%

    No Known Activations