© 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 EvalsExportsinterp-engineNEWAPI 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. 11243
    Prev
    Next
    INDEX
    Explanations

    directives or rules

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to rules and guidelines in communication, particularly in social media contexts

    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
     convergence
    -0.72
     refurb
    -0.68
     pioneering
    -0.64
     upgr
    -0.62
     staggered
    -0.61
     estimated
    -0.61
    trak
    -0.60
     unparalleled
    -0.60
     millenn
    -0.60
     Baz
    -0.59
    POSITIVE LOGITS
     anymore
    1.07
     inappropriately
    0.97
     nor
    0.93
     unnecessarily
    0.85
    iquette
    0.85
     disrespectful
    0.84
    .?
    0.83
     whatsoever
    0.81
     unless
    0.80
     slurs
    0.79
    Activations Density 0.915%

    No Known Activations