© 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 EvalsExportsAPI 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. 2282
    Prev
    Next
    INDEX
    Explanations

    words related to money and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "und" in various 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
    ãĥīãĥ©ãĤ´ãĥ³
    -0.85
    kefeller
    -0.73
    utic
    -0.70
    ======
    -0.70
    fig
    -0.69
    grading
    -0.63
    nect
    -0.61
     toget
    -0.61
    APE
    -0.60
    vert
    -0.59
    POSITIVE LOGITS
    erest
    1.02
    emonium
    0.98
    erer
    0.96
    efined
    0.94
    ered
    0.93
    reth
    0.93
    ecided
    0.90
    rums
    0.90
    lich
    0.90
    oubtedly
    0.89
    Activations Density 0.036%

    No Known Activations