© 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. 11372
    Prev
    Next
    INDEX
    Explanations

    names or words related to Middle Eastern/Qatari places and individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'q'

    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
     Lauder
    -0.61
     Dortmund
    -0.60
     Eclipse
    -0.60
    ufact
    -0.59
     readable
    -0.58
     hect
    -0.57
     chronological
    -0.57
     Oblivion
    -0.57
     Turing
    -0.56
     regenerate
    -0.56
    POSITIVE LOGITS
    aeda
    1.03
    iao
    1.02
    eus
    0.97
    dn
    0.96
    iu
    0.96
    eh
    0.93
    rt
    0.93
    iang
    0.92
    ois
    0.90
    eq
    0.89
    Activations Density 0.032%

    No Known Activations