© 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. 8-RES-JB
    11. 19377
    Prev
    Next
    INDEX
    Explanations

    numerical values that are related to comparisons such as cost, time, and quantity

    oai_token-act-pair · gpt-3.5-turbo

    inquiries regarding the cost of various activities or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.77
    Ń
    -0.69
    §
    -0.68
    \\\\\\\\
    -0.67
    Ĥ¬
    -0.66
    ¥ŀ
    -0.66
    ¢
    -0.65
    ©¶æ
    -0.64
     Cosponsors
    -0.62
     Hels
    -0.62
    POSITIVE LOGITS
    worth
    0.81
     per
    0.81
     allotted
    0.78
    Quantity
    0.75
    Average
    0.72
     expend
    0.72
     allowance
    0.70
     willing
    0.70
     squeeze
    0.70
     apiece
    0.69
    Activations Density 0.246%

    No Known Activations