© 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. 0-RES-JB
    11. 19820
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Meyer" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual, Urban Meyer

    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
     captcha
    -0.84
    gu
    -0.67
     bast
    -0.67
    charg
    -0.66
     giveaway
    -0.66
     ç¥ŀ
    -0.63
     compan
    -0.63
    payers
    -0.63
    quer
    -0.62
     unlocking
    -0.62
    POSITIVE LOGITS
     Meyer
    3.69
    meyer
    1.61
     Yates
    1.09
     Mayer
    1.08
     Petersen
    1.05
     Fuller
    1.04
     Fran
    1.04
     Lyons
    1.03
     Lyon
    1.00
     Meier
    0.98
    Activations Density 0.024%

    No Known Activations