© 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. 11-RES-JB
    11. 3386
    Prev
    Next
    INDEX
    Explanations

    mentions of op-eds from various newspapers

    oai_token-act-pair · gpt-3.5-turbo

    opinion pieces from various publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.70
    enegger
    -0.67
     Tunnel
    -0.67
     Corridor
    -0.64
     Awakens
    -0.64
     Learns
    -0.63
     Ruk
    -0.61
     Kaw
    -0.61
     Saur
    -0.60
     Dign
    -0.60
    POSITIVE LOGITS
    eds
    1.17
    Ed
    0.89
    editor
    0.89
    ed
    0.87
    argument
    0.81
    art
    0.80
    natal
    0.79
    estate
    0.79
    operative
    0.79
    inflammatory
    0.79
    Activations Density 0.038%

    No Known Activations