© 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. 20391
    Prev
    Next
    INDEX
    Explanations

    content urging readers to check something out or follow a call to action

    oai_token-act-pair · gpt-3.5-turbo

    phrases encouraging the reader to check out more content or articles

    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
     suscept
    -0.71
    onte
    -0.67
    lishes
    -0.64
    escent
    -0.62
    essen
    -0.61
    OF
    -0.61
    hene
    -0.60
    oint
    -0.58
     reluct
    -0.57
    iga
    -0.57
    POSITIVE LOGITS
    mate
    1.18
     out
    1.18
    out
    1.01
    boxes
    0.96
     back
    0.95
    lists
    0.94
    mates
    0.91
    outs
    0.86
    points
    0.84
     OUT
    0.84
    Activations Density 0.023%

    No Known Activations