© 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. 10-RES-JB
    11. 796
    Prev
    Next
    INDEX
    Explanations

    sentiments of suspicion or controversy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accusations and unreliability in reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ometers
    -1.17
    stories
    -1.14
    ernels
    -1.06
    iths
    -1.02
    forts
    -1.01
    pieces
    -1.01
    ships
    -1.00
    facts
    -0.99
    types
    -0.98
    events
    -0.97
    POSITIVE LOGITS
     version
    0.97
     batch
    0.96
     instance
    0.92
     chunk
    0.92
     portion
    0.91
     allegation
    0.90
     swath
    0.89
     memorandum
    0.88
     piece
    0.87
     loophole
    0.87
    Activations Density 0.390%

    No Known Activations