© 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. 3-RES-JB
    11. 13150
    Prev
    Next
    INDEX
    Explanations

    words related to legal cases or individuals involved in legal issues, specifically mentioning the term "Jam"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the name "Jam" and its variants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Marketable
    -0.84
     Equality
    -0.67
     Highlander
    -0.66
    enhagen
    -0.65
     Clicker
    -0.64
     Nietzsche
    -0.64
    ģ«
    -0.62
    BuyableInstoreAndOnline
    -0.60
    ledged
    -0.59
    avement
    -0.58
    POSITIVE LOGITS
     Jam
    0.97
    oon
    0.92
    aji
    0.92
    jam
    0.91
    iah
    0.90
    mond
    0.89
    ón
    0.89
    ison
    0.89
    Jam
    0.88
    ming
    0.88
    Activations Density 0.007%

    No Known Activations