© 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. 2-RES-JB
    11. 22043
    Prev
    Next
    INDEX
    Explanations

    the word "Cal" followed by a single digit

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Cal" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.86
    kaya
    -0.83
    erness
    -0.82
    ovych
    -0.77
    icket
    -0.75
    DragonMagazine
    -0.73
    ãģį
    -0.72
    heid
    -0.71
    poke
    -0.66
    lihood
    -0.66
    POSITIVE LOGITS
    endars
    0.99
    ibr
    0.98
    cal
    0.98
    cium
    0.90
    iber
    0.89
     ILCS
    0.87
    tex
    0.84
    culation
    0.83
    Cal
    0.79
    vin
    0.78
    Activations Density 0.008%

    No Known Activations