© 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. 1-RES-JB
    6. 13036
    Prev
    Next
    INDEX
    Explanations

    the name "Mason" or related variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mason."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®å
    -0.69
    eq
    -0.67
    sharing
    -0.66
    upon
    -0.65
    ãģķ
    -0.65
    des
    -0.64
    ãģŁ
    -0.62
    PsyNetMessage
    -0.62
    ded
    -0.62
    sets
    -0.61
    POSITIVE LOGITS
     Mason
    1.21
    hattan
    1.01
    ety
    0.93
    asonry
    0.86
     Dixon
    0.85
    ry
    0.85
    ilyn
    0.82
    uggle
    0.80
     jars
    0.80
    asonic
    0.78
    Activations Density 0.008%

    No Known Activations