© 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. 10415
    Prev
    Next
    INDEX
    Explanations

    mentions of statements or declarations by various entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stated" and its variations, indicating formal declarations or assertions

    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
    fen
    -0.70
    sites
    -0.66
    imet
    -0.65
    lio
    -0.65
    Enlarge
    -0.65
    vernment
    -0.65
    tes
    -0.62
    cent
    -0.61
    xtap
    -0.61
    illions
    -0.61
    POSITIVE LOGITS
     unequivocally
    1.30
     bluntly
    1.18
     emphatically
    1.14
     plainly
    1.08
     categor
    1.00
     confidently
    0.91
     explicitly
    0.88
     definitively
    0.85
     outright
    0.84
    :"
    0.81
    Activations Density 0.061%

    No Known Activations