© 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. 6-RES-JB
    11. 23709
    Prev
    Next
    INDEX
    Explanations

    mentions of glacial periods in Earth's history

    oai_token-act-pair · gpt-3.5-turbo

    terms related to glaciers and ice sheets

    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
    stood
    -0.83
    ÄŁ
    -0.78
    lis
    -0.78
    eers
    -0.73
    riad
    -0.71
    ItemTracker
    -0.70
     stewards
    -0.67
     Nunes
    -0.67
    TAIN
    -0.66
    Rated
    -0.64
    POSITIVE LOGITS
    asses
    1.09
    adiator
    0.96
    ength
    0.90
    ossip
    0.90
    aston
    0.87
    iant
    0.86
    obal
    0.85
    ibrary
    0.83
    oths
    0.83
    oss
    0.83
    Activations Density 0.019%

    No Known Activations