© 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. 7618
    Prev
    Next
    INDEX
    Explanations

    phrases indicating opposition or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of opposition or resistance towards various topics or issues

    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
    seed
    -0.84
    çīĪ
    -0.78
    oufl
    -0.78
    icle
    -0.74
    mberg
    -0.71
    istics
    -0.71
    OGR
    -0.69
    icles
    -0.69
     Tycoon
    -0.65
    ilitating
    -0.62
    POSITIVE LOGITS
     thereto
    0.92
     vehemently
    0.87
     stren
    0.83
    establishment
    0.73
     stances
    0.70
    encing
    0.69
    onent
    0.68
     vigorously
    0.67
    enced
    0.67
     viewpoints
    0.66
    Activations Density 0.054%

    No Known Activations