© 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. 6-RES-JB
    11. 9522
    Prev
    Next
    INDEX
    Explanations

    quotations or statements made by public figures about current events

    oai_token-act-pair · gpt-3.5-turbo

    statements or quotations attributed to public figures in interviews or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brance
    -0.75
    cause
    -0.68
    ecast
    -0.66
    otin
    -0.64
    Ly
    -0.61
    scope
    -0.60
    bish
    -0.60
     boycot
    -0.58
    other
    -0.57
    rett
    -0.57
    POSITIVE LOGITS
     redes
    0.83
    :"
    0.83
     omin
    0.79
     sarcast
    0.79
     newsp
    0.79
    Quote
    0.78
     succinct
    0.77
    terday
    0.77
    outube
    0.76
     Saying
    0.75
    Activations Density 1.135%

    No Known Activations