© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 4247
    Prev
    Next
    INDEX
    Explanations

    phrases related to names, specifically last names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, primarily those with the last name "Keller" or "Heller."

    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
    orough
    -0.68
    edit
    -0.67
    SEC
    -0.64
    lihood
    -0.63
    FY
    -0.62
    office
    -0.61
    Fri
    -0.61
    Es
    -0.61
    Rich
    -0.59
     Obesity
    -0.59
    POSITIVE LOGITS
    onica
    0.98
    gren
    0.97
    idge
    0.95
    kamp
    0.92
    wagen
    0.91
    quist
    0.91
    ocity
    0.90
    mann
    0.89
    stein
    0.88
    anguage
    0.87
    Activations Density 0.008%

    No Known Activations