© 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. 24345
    Prev
    Next
    INDEX
    Explanations

    phrases related to money

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial transactions or monetary issues

    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
    Temperature
    -0.78
    Pont
    -0.73
    ĸļ
    -0.69
    ouver
    -0.68
    Tile
    -0.65
    ãĤ¨ãĥ«
    -0.64
    leigh
    -0.64
    ãĥ´
    -0.63
    Ro
    -0.63
    Sym
    -0.62
    POSITIVE LOGITS
     coffers
    1.11
     dollars
    1.08
     invested
    1.06
     bribe
    1.06
     debit
    1.05
     payable
    1.04
     Investments
    1.03
     cash
    1.02
     investments
    1.01
     repaid
    1.01
    Activations Density 0.601%

    No Known Activations