© 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 EvalsExportsinterp-engineNEWAPI 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. 1188
    Prev
    Next
    INDEX
    Explanations

    locations and events expressed in Spanish

    oai_token-act-pair · gpt-3.5-turbo

    references to urban infrastructure and public spaces

    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
     Flavoring
    -0.70
    sworth
    -0.67
    Spoiler
    -0.67
    Interstitial
    -0.67
    MK
    -0.62
    etheless
    -0.62
    theless
    -0.61
    Sharp
    -0.61
     Morse
    -0.61
     sparks
    -0.60
    POSITIVE LOGITS
    liga
    0.87
    ét
    0.86
    ê
    0.86
    én
    0.84
    ã
    0.83
    ogie
    0.79
    é
    0.79
    è
    0.79
    ibli
    0.76
    idas
    0.76
    Activations Density 0.159%

    No Known Activations