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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 17822
    Prev
    Next
    INDEX
    Explanations

    the name "Dewhurst" in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and institutions, particularly names associated with governance and academia

    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
     Bitcoins
    -0.89
     Rune
    -0.81
     Rabbit
    -0.81
    Anim
    -0.77
     Meta
    -0.77
    Coin
    -0.77
    nir
    -0.75
    à¥
    -0.75
    ombie
    -0.73
     Interstellar
    -0.73
    POSITIVE LOGITS
     Georgetown
    1.80
     Dew
    1.71
     Dwight
    1.69
     Eisenhower
    1.55
     Sev
    1.33
     Riv
    1.32
     Brent
    1.30
     Ike
    1.25
     Gerald
    1.19
     Newt
    1.17
    Activations Density 0.059%

    No Known Activations