© 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. 9-RES-JB
    11. 4692
    Prev
    Next
    INDEX
    Explanations

    insulting or derogatory terms to describe people

    oai_token-act-pair · gpt-3.5-turbo

    harsh insults and derogatory language

    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
    imester
    -0.87
    AMS
    -0.80
    ItemImage
    -0.78
    istry
    -0.77
    conom
    -0.75
    isine
    -0.73
    eton
    -0.69
    ISTORY
    -0.69
    anship
    -0.68
     readiness
    -0.67
    POSITIVE LOGITS
     bunny
    1.26
     bastard
    1.25
     puppy
    1.22
     guy
    1.21
     dude
    1.20
     monkey
    1.19
     bitch
    1.17
     gorilla
    1.17
     ape
    1.17
     jerk
    1.17
    Activations Density 0.664%

    No Known Activations