© 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. 8-RES-JB
    11. 11981
    Prev
    Next
    INDEX
    Explanations

    references to research institutions like the Pew Research Center

    oai_token-act-pair · gpt-3.5-turbo

    references to the Pew Research Center and associated research data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DRAG
    -0.70
     Runner
    -0.63
    abilia
    -0.61
    ynes
    -0.61
     forc
    -0.60
     gearing
    -0.60
     chang
    -0.59
     beet
    -0.59
    yrinth
    -0.59
     centrif
    -0.59
    POSITIVE LOGITS
    aukee
    1.12
    Die
    1.09
    sburg
    1.03
    die
    0.89
     Pew
    0.86
    conn
    0.86
    sonian
    0.83
    sylvania
    0.82
    dor
    0.80
    fam
    0.77
    Activations Density 0.019%

    No Known Activations