© 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. 17852
    Prev
    Next
    INDEX
    Explanations

    sentences discussing possibilities or actions

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or expressions of uncertainty

    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
    lier
    -0.78
    Materials
    -0.74
    foreseen
    -0.72
    istance
    -0.71
    âĵĺ
    -0.71
    growth
    -0.70
    ATS
    -0.68
    contin
    -0.66
    testing
    -0.64
    itiz
    -0.64
    POSITIVE LOGITS
     disagree
    0.97
     seem
    0.96
     scoff
    0.89
    haps
    0.82
     technically
    0.82
     exagger
    0.80
     cringe
    0.77
     chuckle
    0.76
    bes
    0.76
     argue
    0.75
    Activations Density 0.095%

    No Known Activations