© 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. 6-RES-JB
    11. 17329
    Prev
    Next
    INDEX
    Explanations

    numerical values in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, especially related to scores or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NPR
    -0.66
    pmwiki
    -0.65
     heel
    -0.64
    DragonMagazine
    -0.62
     reconc
    -0.61
     respons
    -0.61
     ABE
    -0.61
     gri
    -0.60
     anchors
    -0.59
     juggling
    -0.59
    POSITIVE LOGITS
    engers
    0.70
     NX
    0.63
     Sands
    0.61
     Canary
    0.61
     Surrey
    0.57
     LV
    0.57
    wyn
    0.57
     Tories
    0.57
     Floyd
    0.57
     Clarkson
    0.57
    Activations Density 0.203%

    No Known Activations