© 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. 7686
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to absurdity or ridiculousness

    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
     levers
    -0.82
     allies
    -0.68
     coordin
    -0.67
     volunteers
    -0.67
     moderators
    -0.67
     contractors
    -0.66
     trustees
    -0.66
     pumps
    -0.64
     scanners
    -0.64
     narrowed
    -0.64
    POSITIVE LOGITS
    ieval
    1.08
    reality
    0.99
    oreal
    0.97
    ocalyptic
    0.96
    history
    0.96
    astical
    0.95
    livion
    0.95
    ocide
    0.94
    antasy
    0.91
    ensical
    0.90
    Activations Density 0.434%

    No Known Activations