© 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. 10-RES-JB
    11. 3349
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month Day"

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and numeric data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     1947
    -0.81
     Invaders
    -0.80
    efer
    -0.78
     Jagu
    -0.78
     Lich
    -0.73
    ault
    -0.72
    uka
    -0.72
     Wildcats
    -0.71
     Slov
    -0.71
     Kra
    -0.71
    POSITIVE LOGITS
    10
    1.60
     10
    1.40
    1027
    1.11
     1070
    1.06
    2010
    1.04
    1024
    1.00
    102
    0.99
    105
    0.98
     1050
    0.97
     ten
    0.97
    Activations Density 0.217%

    No Known Activations