© 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. 2-RES-JB
    11. 9522
    Prev
    Next
    INDEX
    Explanations

    adverbs that express a sense of peculiarity or oddity

    oai_token-act-pair · gpt-3.5-turbo

    descriptors conveying unusual, unexpected, or ambiguous qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uese
    -0.73
    tan
    -0.70
    essors
    -0.69
     Dems
    -0.66
    rities
    -0.65
    orem
    -0.65
     Methods
    -0.65
     publication
    -0.64
     Slaughter
    -0.63
     Guys
    -0.63
    POSITIVE LOGITS
     suited
    0.85
     tuned
    0.84
     disple
    0.75
     impressed
    0.74
     alarmed
    0.73
     aroused
    0.72
     fascinated
    0.72
     conceived
    0.70
     situated
    0.70
     confused
    0.70
    Activations Density 0.017%

    No Known Activations