© 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. 11-RES-JB
    11. 12064
    Prev
    Next
    INDEX
    Explanations

    information related to the production and characteristics of coins

    oai_token-act-pair · gpt-3.5-turbo

    information related to coin specifications and denominations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Airbnb
    -1.00
    bnb
    -0.98
    âĶ
    -0.94
    Netflix
    -0.90
     Skype
    -0.85
     therapist
    -0.82
    VPN
    -0.80
     streamed
    -0.80
     Abdel
    -0.79
    Frameworks
    -0.76
    POSITIVE LOGITS
     coins
    1.81
     mint
    1.81
     coin
    1.68
     Mint
    1.67
     Coin
    1.55
     Coins
    1.54
     denominations
    1.44
    mint
    1.36
     counterfe
    1.35
     denomination
    1.35
    Activations Density 0.146%

    No Known Activations