© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10626
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mason" in the text

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly the name "Mason" and its variations

    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
    draw
    -0.77
    cess
    -0.68
    ptroller
    -0.66
    upon
    -0.65
     vested
    -0.64
     Wrest
    -0.64
    PsyNetMessage
    -0.61
    ppo
    -0.61
    ãĥij
    -0.59
    ded
    -0.57
    POSITIVE LOGITS
    ety
    1.02
    hattan
    1.02
     Mason
    1.00
    ry
    0.97
     Dixon
    0.92
     jars
    0.80
    asonic
    0.79
    uth
    0.77
    agements
    0.77
    ulty
    0.77
    Activations Density 0.005%

    No Known Activations