© 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. 15894
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms

    oai_token-act-pair · gpt-3.5-turbo

    economic indicators and factors affecting markets

    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
     differently
    -0.66
    ople
    -0.65
    CI
    -0.63
     OPS
    -0.60
    _.
    -0.59
    icas
    -0.57
     SECTION
    -0.57
    readable
    -0.57
    %:
    -0.56
    cli
    -0.56
    POSITIVE LOGITS
     coupled
    1.19
     prevents
    1.14
     ensured
    1.09
     resulted
    1.07
     preclude
    1.04
     ensures
    1.04
     overwhel
    1.03
     prevented
    1.03
     translates
    0.99
     dissu
    0.97
    Activations Density 0.580%

    No Known Activations