© 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. 9503
    Prev
    Next
    INDEX
    Explanations

    references to the Sundance Film Festival

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly related to the Sundance Film Festival and individuals associated with it

    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
    vernment
    -0.80
    quit
    -0.74
    cules
    -0.72
    uliffe
    -0.71
    veyard
    -0.71
     therap
    -0.71
    TAIN
    -0.69
    ked
    -0.69
     chicks
    -0.69
    metics
    -0.68
    POSITIVE LOGITS
    erer
    1.11
    erers
    1.03
    ere
    0.99
    ered
    0.94
    orf
    0.93
    ell
    0.89
    ouble
    0.87
    ezvous
    0.87
    ele
    0.87
    ragon
    0.86
    Activations Density 0.019%

    No Known Activations