© 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. 2-RES-JB
    11. 8935
    Prev
    Next
    INDEX
    Explanations

    keywords related to something being extraordinary, exceptional, or never done before

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unprecedented."

    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
    claimer
    -0.80
    apa
    -0.70
    burn
    -0.70
    yard
    -0.70
    uv
    -0.68
    point
    -0.68
    uay
    -0.66
    wives
    -0.65
    tein
    -0.65
    omo
    -0.64
    POSITIVE LOGITS
     unprecedented
    0.98
    wcs
    0.91
    ly
    0.81
    aneously
    0.79
     unanim
    0.75
    ially
    0.75
     revelations
    0.73
    LY
    0.72
    ITIES
    0.71
     amounts
    0.71
    Activations Density 0.006%

    No Known Activations