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

    Neuronpedia

    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. 4-RES-JB
    11. 17077
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Fabian" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Fabio" or variations of it, indicating a focus on this specific individual

    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
    FTWARE
    -0.87
     whales
    -0.70
     ot
    -0.69
    avez
    -0.67
    bilt
    -0.67
     Anchorage
    -0.65
    WARE
    -0.62
     Miko
    -0.62
    xual
    -0.62
    creen
    -0.61
    POSITIVE LOGITS
    rics
    1.44
    rique
    1.41
    ulous
    1.35
    rik
    1.23
    ulously
    1.20
    ric
    1.09
    ulum
    1.05
    ienne
    1.01
    rica
    1.00
     Fab
    0.99
    Activations Density 0.014%

    No Known Activations