© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 8489
    Prev
    Next
    INDEX
    Explanations

    numeric values that are related to time or quantities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acas
    -0.73
    algia
    -0.69
    ¬¼
    -0.68
     guiActiveUn
    -0.63
    hran
    -0.62
    izen
    -0.62
    Ĥª
    -0.61
    abouts
    -0.60
    uyomi
    -0.60
    sein
    -0.59
    POSITIVE LOGITS
     whereas
    1.47
     but
    1.14
     meaning
    1.14
     although
    1.12
     followed
    1.07
     regardless
    1.05
     irrespective
    1.05
     implying
    1.02
     while
    1.02
     except
    1.02
    Activations Density 0.307%

    No Known Activations