© 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. 0-RES-JB
    11. 5399
    Prev
    Next
    INDEX
    Explanations

    words related to disagreement or contrasting opinions

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iak
    -0.65
     Regist
    -0.65
     Lif
    -0.64
     Harvest
    -0.61
     Lite
    -0.56
     Lets
    -0.55
    net
    -0.55
    Ra
    -0.55
     Olsen
    -0.55
     Speed
    -0.54
    POSITIVE LOGITS
     disagree
    3.81
     disagrees
    2.44
     disagreed
    2.43
     disagreement
    1.79
    agree
    1.72
     agree
    1.70
     differ
    1.61
     disagreements
    1.57
     disapprove
    1.46
     contradict
    1.31
    Activations Density 0.018%

    No Known Activations