© 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. 22915
    Prev
    Next
    INDEX
    Explanations

    year-related terms

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific references to years

    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
    icago
    -0.84
    uca
    -0.73
    ĸļ
    -0.73
    hran
    -0.72
    ongyang
    -0.67
    stadt
    -0.64
    ousy
    -0.64
    uably
    -0.64
    ijuana
    -0.64
    culosis
    -0.64
    POSITIVE LOGITS
     explanatory
    0.90
     acron
    0.90
     submissions
    0.82
     organizational
    0.81
     hypotheses
    0.78
     methodological
    0.78
     strateg
    0.77
     datasets
    0.74
     variables
    0.74
     observations
    0.73
    Activations Density 1.156%

    No Known Activations