© 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. 8-RES-JB
    11. 640
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms and data

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time series and comparisons over time

    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
    UTF
    -0.63
    ŃĶ
    -0.58
    ãĤª
    -0.54
     sts
    -0.54
     dissenting
    -0.53
    ãĥķãĤ©
    -0.53
    enegger
    -0.53
     TRAN
    -0.51
     FANT
    -0.51
     exceptions
    -0.50
    POSITIVE LOGITS
    instance
    0.78
    gression
    0.65
    gallery
    0.64
    fecture
    0.64
    atown
    0.64
    opausal
    0.64
    century
    0.63
    endment
    0.62
    grand
    0.61
    bas
    0.61
    Activations Density 0.072%

    No Known Activations