© 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. 8-RES-JB
    11. 14820
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or refutation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ean
    -0.75
    rn
    -0.73
    gypt
    -0.70
    lish
    -0.69
     Appears
    -0.69
    Ott
    -0.68
    otton
    -0.67
    lean
    -0.67
    agents
    -0.66
    late
    -0.66
    POSITIVE LOGITS
     shortage
    1.28
     doubt
    1.23
     indication
    1.16
     guarantee
    1.06
     reason
    1.05
     ambiguity
    0.97
     hesitation
    0.95
     excuse
    0.95
     longer
    0.94
     denying
    0.94
    Activations Density 0.061%

    No Known Activations