© 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. 9-RES-JB
    11. 13671
    Prev
    Next
    INDEX
    Explanations

    gendered insults and terms related to technology

    oai_token-act-pair · gpt-3.5-turbo

    derogatory terms related to geek and nerd culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angan
    -0.77
    large
    -0.68
    aeda
    -0.67
    arbon
    -0.67
    ij
    -0.67
     conduc
    -0.65
     Incre
    -0.62
    Contents
    -0.61
    CLOSE
    -0.61
    ilion
    -0.60
    POSITIVE LOGITS
    gery
    1.20
     extraord
    1.19
    hood
    1.19
    dom
    1.10
     who
    1.01
    ishly
    0.98
    ism
    0.95
    doms
    0.95
    ry
    0.92
    isms
    0.92
    Activations Density 0.402%

    No Known Activations