© 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. 3-RES-JB
    11. 5591
    Prev
    Next
    INDEX
    Explanations

    sources of information or quotes in text

    oai_token-act-pair · gpt-3.5-turbo

    references to anonymous or named sources in statements or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeper
    -0.94
    ellen
    -0.90
    wagen
    -0.87
     satell
    -0.79
    interstitial
    -0.77
    creen
    -0.76
    Ħ¢
    -0.76
    andel
    -0.76
    orks
    -0.75
    itters
    -0.75
    POSITIVE LOGITS
     source
    1.09
     sources
    1.03
    source
    1.03
    Fed
    0.92
     Sources
    0.91
    books
    0.81
    forge
    0.79
     sourcing
    0.74
    finding
    0.74
    Sources
    0.72
    Activations Density 0.021%

    No Known Activations