© 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. 8-RES-JB
    11. 11352
    Prev
    Next
    INDEX
    Explanations

    references to different sizes or dimensions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to measurements or dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oother
    -0.72
    oner
    -0.72
    FB
    -0.71
    ================================================================
    -0.69
    PsyNetMessage
    -0.67
    PLA
    -0.67
    uctions
    -0.66
    autions
    -0.65
     Practices
    -0.64
    ctive
    -0.64
    POSITIVE LOGITS
     Everest
    0.78
     postage
    0.76
     Tyrann
    0.74
     Jupiter
    0.69
     orbiting
    0.69
     thous
    0.69
     grains
    0.68
     Pluto
    0.67
     lettuce
    0.66
     iceberg
    0.66
    Activations Density 0.163%

    No Known Activations