© 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. 6-RES-JB
    11. 12835
    Prev
    Next
    INDEX
    Explanations

    verbs related to negative characterization or treatment of individuals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the marginalization and denigration of individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venture
    -0.69
     horizont
    -0.68
     arrang
    -0.67
    querque
    -0.66
    uid
    -0.66
    shake
    -0.65
    quart
    -0.65
    vent
    -0.65
    chart
    -0.64
    aldo
    -0.64
    POSITIVE LOGITS
     slurs
    0.76
     stereotypes
    0.76
     insults
    0.74
    enance
    0.72
     caricature
    0.72
     Enemy
    0.71
     bullies
    0.70
     homosexuals
    0.69
     foreigners
    0.69
     Koreans
    0.68
    Activations Density 0.123%

    No Known Activations