© 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. 13719
    Prev
    Next
    INDEX
    Explanations

    words related to values, costs, estimations, and financial figures

    oai_token-act-pair · gpt-3.5-turbo

    monetary valuations and estimations

    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
    ppo
    -0.60
    uria
    -0.58
    mare
    -0.58
     disembark
    -0.57
     Flavoring
    -0.57
     notice
    -0.56
    sense
    -0.56
    vas
    -0.55
    ocent
    -0.55
    warts
    -0.55
    POSITIVE LOGITS
     at
    1.00
     somewhere
    0.87
    ¶æ
    0.82
    At
    0.81
     between
    0.74
     upwards
    0.72
     anywhere
    0.72
    ª
    0.70
    =~
    0.70
    atively
    0.70
    Activations Density 0.153%

    No Known Activations