© 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. 5491
    Prev
    Next
    INDEX
    Explanations

    mentions of names and terms related to legal or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and relationships that may indicate conflict or division

    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
    esc
    -0.72
    externalActionCode
    -0.72
    otle
    -0.68
    hell
    -0.66
    once
    -0.63
    adapt
    -0.62
    osta
    -0.62
    Champ
    -0.62
    ignty
    -0.61
    essors
    -0.61
    POSITIVE LOGITS
    nesday
    1.31
    bed
    0.93
    bing
    0.89
    nec
    0.86
    aukee
    0.82
     wedge
    0.82
     Weiner
    0.80
    vy
    0.80
    cles
    0.79
    nexus
    0.78
    Activations Density 0.069%

    No Known Activations