© 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. 9-RES-JB
    11. 17732
    Prev
    Next
    INDEX
    Explanations

    mentions of the music festival "Glastonbury"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location "Glastonbury."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reincarn
    -0.68
     Warrant
    -0.65
    ENTION
    -0.62
    Lago
    -0.61
     DRAG
    -0.61
    FTWARE
    -0.60
     actionGroup
    -0.59
     Jou
    -0.59
    lesi
    -0.58
    ãĥīãĥ©
    -0.58
    POSITIVE LOGITS
    gow
    1.09
    furt
    0.96
    haven
    0.83
    coe
    0.82
    estones
    0.80
    voy
    0.75
    agall
    0.75
    cester
    0.74
    agles
    0.73
    wegian
    0.72
    Activations Density 0.088%

    No Known Activations