© 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. 16046
    Prev
    Next
    INDEX
    Explanations

    contractions with "don't"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I don't" expressing negation or refusal

    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
     eleph
    -0.96
     pione
    -0.90
     exting
    -0.88
    Þ
    -0.88
     enthusi
    -0.87
    ò
    -0.86
    aditional
    -0.85
     practition
    -0.84
     newcom
    -0.84
    ñ
    -0.82
    POSITIVE LOGITS
    't
    1.67
    ned
    1.07
    ´
    0.91
    ÃŃ
    0.81
    ovan
    0.78
    iversity
    0.76
    fortunately
    0.75
    Ê
    0.75
    `
    0.74
    ates
    0.74
    Activations Density 0.090%

    No Known Activations