© 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. 10804
    Prev
    Next
    INDEX
    Explanations

    phrases related to discrimination or prejudice

    oai_token-act-pair · gpt-3.5-turbo

    instances of discrimination or bias against 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
    starter
    -0.78
    bridge
    -0.76
    facing
    -0.74
    cano
    -0.73
    widget
    -0.72
    chart
    -0.72
    orah
    -0.70
    rez
    -0.70
    ortium
    -0.68
    Scope
    -0.67
    POSITIVE LOGITS
     helpless
    0.75
     behalf
    0.64
     them
    0.64
     extraord
    0.64
     abuses
    0.63
     abuse
    0.62
     perfection
    0.62
     anx
    0.61
     cruelty
    0.60
     herds
    0.60
    Activations Density 0.229%

    No Known Activations