© 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. 9-RES-JB
    11. 11346
    Prev
    Next
    INDEX
    Explanations

    shortened forms of "financial technology" (fintech)

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fintech" and its derivatives

    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
    OAD
    -0.67
    gypt
    -0.66
     Unsure
    -0.65
    brates
    -0.62
    ciating
    -0.62
     resil
    -0.62
    pta
    -0.61
     millenn
    -0.61
    jriwal
    -0.60
    days
    -0.60
    POSITIVE LOGITS
    ellect
    1.13
    ypes
    1.08
    eki
    1.02
    elligent
    1.01
    angible
    0.92
    essential
    0.88
    illation
    0.88
    rust
    0.86
    yre
    0.85
    oki
    0.85
    Activations Density 0.040%

    No Known Activations