© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14827
    Prev
    Next
    INDEX
    Explanations

    adverbs that express contrasting or opposing relationships

    oai_token-act-pair · gpt-3.5-turbo

    transition words and phrases that indicate contrast or example in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -1.05
     nomine
    -0.94
     pione
    -0.89
     tremend
    -0.89
    Þ
    -0.87
     eleph
    -0.83
     destro
    -0.82
     neighb
    -0.82
     tyr
    -0.79
     occas
    -0.79
    POSITIVE LOGITS
    ,
    0.94
    Merit
    0.82
    .,
    0.74
    ,.
    0.68
    ,,
    0.67
    ,[
    0.66
    !,
    0.64
    ,...
    0.60
    ,-
    0.60
    ,,,,,,,,
    0.58
    Activations Density 0.080%

    No Known Activations