© 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. 7-RES-JB
    11. 20885
    Prev
    Next
    INDEX
    Explanations

    expletives and profanity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to confusion and absurdity in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.77
     Qiao
    -0.68
     Regulatory
    -0.67
     Fiscal
    -0.65
     Ernst
    -0.64
     Referred
    -0.64
     Citation
    -0.63
     Thomson
    -0.62
     HHS
    -0.62
     Deutsche
    -0.62
    POSITIVE LOGITS
    fuck
    1.03
    shit
    0.99
     haha
    0.87
     crap
    0.87
     shit
    0.85
     ;)
    0.84
    itty
    0.83
     fuckin
    0.82
     bitch
    0.81
     fuck
    0.80
    Activations Density 0.715%

    No Known Activations