© 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 EvalsExportsAPI 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. 10-RES-JB
    11. 3404
    Prev
    Next
    INDEX
    Explanations

    technical terms and topics related to technology and media

    oai_token-act-pair · gpt-3.5-turbo

    references to specific journalism formats or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     looph
    -0.67
    amous
    -0.65
    specified
    -0.65
    wikipedia
    -0.64
    adra
    -0.64
    acting
    -0.64
    Īè
    -0.64
    drawn
    -0.62
    mop
    -0.61
    usable
    -0.61
    POSITIVE LOGITS
     Podcast
    1.28
     Newsletter
    1.22
     podcast
    1.18
     Magazine
    1.09
     magazine
    1.08
    âĦ¢
    1.07
     newsletter
    1.06
     contributor
    1.02
     Blog
    1.01
     columnist
    1.00
    Activations Density 0.276%

    No Known Activations