© 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. 23909
    Prev
    Next
    INDEX
    Explanations

    references to popular television shows and cultural figures

    oai_token-act-pair · gpt-3.5-turbo

    phrases or references related to popular television shows or series

    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
     mistakenly
    -0.79
     metic
    -0.72
     reflex
    -0.69
     purported
    -0.66
     packed
    -0.64
     draw
    -0.64
     approximate
    -0.64
     wrapped
    -0.64
     vaguely
    -0.64
     suppose
    -0.63
    POSITIVE LOGITS
    audi
    1.12
    Pand
    1.02
    Pont
    1.02
    Vi
    1.01
    License
    0.99
    AUT
    0.99
    Da
    0.99
    commun
    0.98
    lux
    0.97
    nob
    0.97
    Activations Density 0.112%

    No Known Activations