© 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. 6-RES-JB
    11. 9253
    Prev
    Next
    INDEX
    Explanations

    mentions of geopolitical and political events related to a specific place or region

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Burdur" or related variations, indicating a focus on location or associated events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asers
    -0.67
    weeney
    -0.64
    xual
    -0.63
     Investors
    -0.59
    SEC
    -0.59
     Cobra
    -0.58
    glers
    -0.57
    xon
    -0.56
    Bee
    -0.54
    bard
    -0.54
    POSITIVE LOGITS
    itives
    1.19
    erer
    0.98
    s
    0.89
    itive
    0.86
    sworth
    0.84
    erers
    0.83
    istani
    0.82
    aby
    0.81
    edIn
    0.81
    nant
    0.81
    Activations Density 0.023%

    No Known Activations