© 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. 6-RES-JB
    11. 12084
    Prev
    Next
    INDEX
    Explanations

    elements related to software development, technology, and coding

    oai_token-act-pair · gpt-3.5-turbo

    references to business entities and interactions related to them

    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
    âĢİ
    -0.59
     âĢİ
    -0.58
     .)
    -0.58
    âĢ¦)
    -0.54
     Forth
    -0.50
    .).
    -0.48
     Imran
    -0.48
     Gerr
    -0.47
    Merit
    -0.47
    .)
    -0.47
    POSITIVE LOGITS
    ogram
    0.55
    olate
    0.52
    rontal
    0.52
    omon
    0.50
    apest
    0.49
    poons
    0.49
    zeb
    0.48
    cellaneous
    0.48
    azines
    0.48
    mosp
    0.47
    Activations Density 0.698%

    No Known Activations