© 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. 24409
    Prev
    Next
    INDEX
    Explanations

    negative implications or restrictions indicated by the word "not"

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating exclusions or limitations

    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
    fail
    -0.64
     Puzz
    -0.62
    itiveness
    -0.60
    HAEL
    -0.59
    _-_
    -0.59
    assetsadobe
    -0.59
    roo
    -0.57
    manship
    -0.57
     underest
    -0.56
    issance
    -0.56
    POSITIVE LOGITS
     necessarily
    1.18
     otherwise
    1.13
     ordinarily
    1.07
     explicitly
    0.99
     yet
    0.99
     normally
    0.95
     expressly
    0.94
     already
    0.86
     traditionally
    0.85
     overtly
    0.83
    Activations Density 0.172%

    No Known Activations