© 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. 11-RES-JB
    11. 11887
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong opinions or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article 'a' in various contexts indicating types or categories

    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
    effects
    -0.74
    units
    -0.73
    notes
    -0.69
    ews
    -0.67
    DragonMagazine
    -0.66
    hours
    -0.66
    agues
    -0.65
    Versions
    -0.65
    anqu
    -0.64
    IED
    -0.64
    POSITIVE LOGITS
     shame
    1.46
     pity
    1.40
     testament
    1.08
     misconception
    1.04
     coincidence
    1.02
     tricky
    0.99
     miracle
    0.98
     fascinating
    0.98
     wonder
    0.98
     daunting
    0.97
    Activations Density 0.139%

    No Known Activations