© 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 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. 3-RES-JB
    11. 3578
    Prev
    Next
    INDEX
    Explanations

    derogatory terms or insults

    oai_token-act-pair · gpt-3.5-turbo

    derogatory terms used to describe women

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mental
    -0.79
    HCR
    -0.77
     ceremonial
    -0.71
    apers
    -0.71
    tnc
    -0.67
    inguished
    -0.67
     srf
    -0.66
    Gaza
    -0.66
     kindred
    -0.65
    Vert
    -0.64
    POSITIVE LOGITS
     bitch
    1.05
    hole
    1.04
    fuck
    0.99
    holes
    0.94
    buster
    0.92
    bags
    0.92
    dump
    0.85
     cunt
    0.83
    loads
    0.81
    cake
    0.80
    Activations Density 0.017%

    No Known Activations