© 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. 1-RES-JB
    11. 14295
    Prev
    Next
    INDEX
    Explanations

    opponents or critics of various plans, laws, or policies

    oai_token-act-pair · gpt-3.5-turbo

    words related to opposition or opponents in discussions and debates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oÄŁ
    -0.85
    MER
    -0.82
    vol
    -0.76
    beit
    -0.75
    cow
    -0.71
    loaded
    -0.70
     reckoning
    -0.65
    seed
    -0.64
    forward
    -0.64
    mer
    -0.63
    POSITIVE LOGITS
    onents
    1.31
    iants
    0.86
    onent
    0.80
     concede
    0.77
     Flavoring
    0.75
    terness
    0.75
    hesis
    0.72
    ractor
    0.72
    itute
    0.71
     Wrest
    0.71
    Activations Density 0.021%

    No Known Activations