© 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. 10-RES-JB
    11. 18945
    Prev
    Next
    INDEX
    Explanations

    quotes and messages in a structured conversation

    oai_token-act-pair · gpt-3.5-turbo

    references to quotes and authorship in text

    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
    agos
    -0.80
    aucas
    -0.78
    oulos
    -0.77
    essen
    -0.73
    hop
    -0.72
    etting
    -0.70
    LOS
    -0.70
    alore
    -0.69
     silhou
    -0.67
    otom
    -0.67
    POSITIVE LOGITS
     Originally
    1.04
     Posted
    1.04
     Quote
    0.84
     Posts
    0.79
     ·
    0.79
    Quote
    0.77
     Rating
    0.76
     Thread
    0.75
     Password
    0.74
    Posts
    0.73
    Activations Density 0.043%

    No Known Activations