© 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. 4-RES-JB
    11. 10204
    Prev
    Next
    INDEX
    Explanations

    the surname "Mayer"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly with the surname Mayer

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

    No Comments

    Negative Logits
    lihood
    -0.90
    mble
    -0.84
    ŃĶ
    -0.82
    ebook
    -0.72
    ives
    -0.68
    itness
    -0.68
    ords
    -0.67
    ¬¼
    -0.67
    ruciating
    -0.66
    ibles
    -0.66
    POSITIVE LOGITS
    tz
    0.99
     Mayer
    0.87
    dinand
    0.83
     Rothschild
    0.78
    rh
    0.71
    ton
    0.70
    geist
    0.69
    antics
    0.67
    anyahu
    0.66
    lein
    0.65
    Activations Density 0.018%

    No Known Activations