© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 437
    Prev
    Next
    INDEX
    Explanations

    the accented letter 'ú'

    oai_token-act-pair · gpt-4-turbo

    accents and specific characters

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols that appear frequently in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hayward
    -0.72
    ardy
    -0.64
    addons
    -0.64
     Cosponsors
    -0.64
    oring
    -0.63
    Reviewed
    -0.61
     lacking
    -0.60
    aunders
    -0.60
    IPS
    -0.59
    imer
    -0.59
    POSITIVE LOGITS
    cus
    0.88
    lio
    0.88
    ú
    0.87
    ternity
    0.87
    ÃįÃį
    0.82
    ð
    0.82
    rio
    0.79
    ption
    0.76
    sson
    0.76
    rican
    0.76
    Activations Density 0.004%

    No Known Activations