© 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. 11-RES-JB
    11. 5073
    Prev
    Next
    INDEX
    Explanations

    years and months in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    specific years and their corresponding months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cephal
    -0.76
    emonic
    -0.73
    uth
    -0.68
    IRE
    -0.68
    870
    -0.68
     770
    -0.67
    tnc
    -0.66
    laus
    -0.65
    IZ
    -0.65
     670
    -0.62
    POSITIVE LOGITS
    ĭ
    0.77
    cake
    0.73
    ento
    0.72
    tag
    0.69
    ãĥĩãĤ£
    0.67
    ategories
    0.66
    ãĥ¼ãĥĨãĤ£
    0.64
    inal
    0.62
    ulet
    0.59
    iston
    0.59
    Activations Density 0.038%

    No Known Activations