© 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. 4-RES-JB
    11. 6539
    Prev
    Next
    INDEX
    Explanations

    negations in sentences

    oai_token-act-pair · gpt-3.5-turbo

    negations or expressions indicating uncertainty

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

    No Comments

    Negative Logits
     Fuji
    -0.75
     Strategy
    -0.73
     è
    -0.67
     é
    -0.62
     Magn
    -0.62
    facts
    -0.62
     Circuit
    -0.61
     Mant
    -0.61
     Culture
    -0.60
     Inventory
    -0.60
    POSITIVE LOGITS
    icably
    1.13
     necessarily
    1.13
    epad
    0.99
    hin
    0.98
    icable
    0.97
     bother
    0.92
    necess
    0.89
     hesitate
    0.85
    ched
    0.84
     skim
    0.80
    Activations Density 0.042%

    No Known Activations