Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5536
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Matt"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, particularly the name "Matt."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibrary
    -0.94
    ynthesis
    -0.77
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.77
    avorite
    -0.76
    ipedia
    -0.76
    perty
    -0.74
    etus
    -0.73
    wikipedia
    -0.72
    inus
    -0.72
    pload
    -0.71
    POSITIVE LOGITS
     pain
    0.89
    pain
    0.81
     Pain
    0.72
    Pain
    0.72
    hol
    0.71
     Trend
    0.66
     Horror
    0.63
    temp
    0.62
     Mazda
    0.61
    mess
    0.61
    Activations Density 0.000%

    No Known Activations