© 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. 8-RES-JB
    11. 7933
    Prev
    Next
    INDEX
    Explanations

    phrases containing profanity and aggressive language

    oai_token-act-pair · gpt-3.5-turbo

    cussed or vulgar language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.86
     Ambro
    -0.85
    Enlarge
    -0.73
     Nicol
    -0.73
     Vend
    -0.72
     departures
    -0.71
     strikingly
    -0.71
     Thib
    -0.70
     Woodward
    -0.69
     Virt
    -0.68
    POSITIVE LOGITS
    fuck
    1.28
     fuckin
    1.17
    shit
    1.16
     bitch
    1.13
     fuck
    1.12
     cunt
    1.11
    oooo
    1.10
    ****
    1.10
     shit
    1.09
    aaaa
    1.06
    Activations Density 0.327%

    No Known Activations