© 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. 20738
    Prev
    Next
    INDEX
    Explanations

    numerical information related to time periods

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of fiscal periods or reporting timelines

    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
    hend
    -0.70
    JR
    -0.68
    borgh
    -0.62
    estern
    -0.61
    HCR
    -0.59
    ipher
    -0.59
    rm
    -0.58
    Redd
    -0.58
    heastern
    -0.58
    enegger
    -0.56
    POSITIVE LOGITS
    endment
    0.82
     anniversary
    0.77
     bye
    0.71
    iversary
    0.69
     probation
    0.66
    redits
    0.66
     update
    0.63
    ago
    0.63
    aez
    0.63
    pled
    0.62
    Activations Density 0.125%

    No Known Activations