© 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. 10-RES-JB
    11. 13840
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers in dates

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to dates, numerical references, and categories

    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
    oco
    -0.95
     Alec
    -0.88
    ogen
    -0.85
    igs
    -0.84
    igraph
    -0.84
     Cob
    -0.82
     Io
    -0.82
     AST
    -0.80
    æ©
    -0.79
     Tob
    -0.79
    POSITIVE LOGITS
    month
    0.94
    ¹
    0.92
     Neph
    0.89
    ¸
    0.87
     membranes
    0.83
     Monthly
    0.82
     month
    0.82
    Month
    0.81
    neum
    0.81
     pad
    0.79
    Activations Density 0.433%

    No Known Activations