© 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. 16085
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences expressing uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or possibility

    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
    cies
    -0.80
    ocaust
    -0.77
    ament
    -0.76
    arthed
    -0.75
    atches
    -0.73
    uments
    -0.72
    emale
    -0.70
    iak
    -0.69
    dayName
    -0.68
    pit
    -0.68
    POSITIVE LOGITS
     someday
    1.37
     even
    0.96
     sooner
    0.91
     thats
    0.85
     they
    0.84
     somebody
    0.83
     we
    0.81
     someone
    0.79
     unsurprisingly
    0.79
     it
    0.78
    Activations Density 0.055%

    No Known Activations