© 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. 8-RES-JB
    11. 22594
    Prev
    Next
    INDEX
    Explanations

    references to the word "Urbana"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "Ur."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.80
     Scarlet
    -0.79
    washer
    -0.73
     Sins
    -0.72
    atform
    -0.71
     Dickinson
    -0.67
     Clarkson
    -0.64
    eting
    -0.64
     brackets
    -0.62
    NetMessage
    -0.62
    POSITIVE LOGITS
    gent
    1.22
    seless
    1.05
    gery
    1.05
    gencies
    1.03
    gency
    1.01
    du
    0.99
    gently
    0.98
    pee
    0.95
    inary
    0.93
    bers
    0.92
    Activations Density 0.025%

    No Known Activations