© 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. 9-RES-JB
    11. 22657
    Prev
    Next
    INDEX
    Explanations

    instances where the text expresses a lack, insufficiency, or negation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate uncertainty or insufficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cens
    -0.75
    mis
    -0.71
    undrum
    -0.70
     understatement
    -0.68
    but
    -0.67
    negative
    -0.66
    iferation
    -0.64
    less
    -0.63
    ructose
    -0.63
    misc
    -0.62
    POSITIVE LOGITS
    etheless
    0.87
     conclusive
    0.75
     nonetheless
    0.74
     concrete
    0.72
     enough
    0.71
    cially
    0.69
     necessarily
    0.67
     guarantee
    0.66
     sufficient
    0.63
    estamp
    0.61
    Activations Density 0.428%

    No Known Activations