© 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. 11259
    Prev
    Next
    INDEX
    Explanations

    references to percentages, numbers, and quantities in relation to economic or financial contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to economic metrics and statistics

    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
    ĪĴ
    -0.81
    æĦ
    -0.75
     abound
    -0.71
    kered
    -0.63
     fences
    -0.61
     extraord
    -0.60
     diction
    -0.58
     remorse
    -0.58
     Maw
    -0.57
    ħĭ
    -0.56
    POSITIVE LOGITS
     apiece
    0.89
     annually
    0.87
     excluding
    0.86
     (~
    0.86
     worldwide
    0.81
    *.
    0.81
     nationwide
    0.79
     (£
    0.79
     total
    0.78
     attributable
    0.75
    Activations Density 0.241%

    No Known Activations