© 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. 7-RES-JB
    11. 23926
    Prev
    Next
    INDEX
    Explanations

    the name or variations of the name "Toulon"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the suffix "oul" in names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skywalker
    -0.66
     STOR
    -0.66
    909
    -0.59
    xon
    -0.59
    PRESS
    -0.59
    ãĥ¼ãĥ³
    -0.58
     Reloaded
    -0.58
     2022
    -0.58
     Raiders
    -0.58
     buckle
    -0.57
    POSITIVE LOGITS
    ouse
    1.04
    teenth
    0.99
    oir
    0.98
    inic
    0.97
    otaur
    0.93
    igans
    0.93
    oise
    0.90
    otine
    0.90
    iquid
    0.85
    mosp
    0.82
    Activations Density 0.022%

    No Known Activations