© 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. 11-RES-JB
    11. 20493
    Prev
    Next
    INDEX
    Explanations

    quotes and statements made by various individuals

    oai_token-act-pair · gpt-3.5-turbo

    reported speech or quotes from individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resist
    -0.69
    aughtered
    -0.65
    pend
    -0.65
     nonviolent
    -0.61
     prosecutions
    -0.59
    hovah
    -0.59
    poses
    -0.58
     repressive
    -0.57
     Soros
    -0.57
     arsenic
    -0.56
    POSITIVE LOGITS
     afterward
    1.26
     afterwards
    1.11
     Thursday
    0.95
     Monday
    0.94
     after
    0.93
     Wednesday
    0.92
     midway
    0.89
     Friday
    0.89
     Tuesday
    0.89
     preseason
    0.88
    Activations Density 0.187%

    No Known Activations