© 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. 3493
    Prev
    Next
    INDEX
    Explanations

    terms related to aspects of controversy or separate entities

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to investigation, controversy, and separation

    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
    osponsors
    -1.02
    stories
    -1.01
    resses
    -0.93
    forts
    -0.92
    ravings
    -0.92
    stars
    -0.92
    effects
    -0.92
    izons
    -0.91
    events
    -0.91
    results
    -0.91
    POSITIVE LOGITS
     swath
    1.01
     batch
    0.91
     loophole
    0.91
     attempt
    0.88
     piece
    0.87
     initiative
    0.87
     lawsuit
    0.86
     agreement
    0.86
     allegation
    0.84
     spate
    0.84
    Activations Density 0.307%

    No Known Activations