© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18697
    Prev
    Next
    INDEX
    Explanations

    references to previous works or articles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reference to prior content or previous discussions

    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
    $$$$
    -0.79
    orsche
    -0.67
    BY
    -0.65
    orean
    -0.65
    arov
    -0.64
    ereo
    -0.62
    adle
    -0.61
     scissors
    -0.60
    aren
    -0.60
     restores
    -0.59
    POSITIVE LOGITS
     blog
    1.12
     article
    1.08
     blogs
    1.06
     articles
    1.03
    blogs
    0.96
     posts
    0.92
     Blog
    0.91
     discussing
    0.89
    blog
    0.88
     column
    0.86
    Activations Density 0.268%

    No Known Activations