© 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. 5914
    Prev
    Next
    INDEX
    Explanations

    dates in the format Month DD, YYYY

    oai_token-act-pair · gpt-3.5-turbo

    date and time information

    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
     Heavenly
    -0.68
     abusers
    -0.67
     Chandra
    -0.64
    orses
    -0.63
     Notting
    -0.63
     Realms
    -0.62
     comparisons
    -0.62
     Elastic
    -0.61
     Mechdragon
    -0.61
     livest
    -0.61
    POSITIVE LOGITS
    04
    1.83
    03
    1.79
    06
    1.77
    05
    1.75
    02
    1.73
    07
    1.70
    08
    1.67
     02
    1.56
    09
    1.55
     03
    1.53
    Activations Density 0.050%

    No Known Activations