© 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. 9-RES-JB
    11. 7195
    Prev
    Next
    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and points of interest

    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
    •Every Saturdays, Rabbi Goldstein goes to the
    to the

    No Comments

    Negative Logits
    ankind
    -0.72
    standing
    -0.66
     @@
    -0.66
    etheless
    -0.66
    ãĥĥãĥĪ
    -0.65
     tagging
    -0.63
    vich
    -0.61
     depended
    -0.61
    idae
    -0.61
    stood
    -0.60
    POSITIVE LOGITS
     shrine
    1.00
     funer
    0.98
     hospital
    0.94
     funeral
    0.91
     synagogue
    0.91
     dentist
    0.90
     meetings
    0.89
     temple
    0.89
     clinic
    0.88
     mosque
    0.87
    Activations Density 0.382%

    No Known Activations