© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11282
    Prev
    Next
    INDEX
    Explanations

    superlatives denoting the biggest or the highest in different contexts and subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to entities or groups that hold the status of "largest" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fy
    -0.69
    worms
    -0.61
     substitute
    -0.61
     flashes
    -0.58
    Pass
    -0.58
     Logged
    -0.57
    ****
    -0.57
    tty
    -0.57
     Dame
    -0.56
    touch
    -0.56
    POSITIVE LOGITS
     largest
    3.31
    largest
    2.70
     biggest
    2.33
     smallest
    2.15
     longest
    2.08
     tallest
    2.03
     widest
    1.97
     oldest
    1.87
     heaviest
    1.86
     highest
    1.79
    Activations Density 0.016%

    No Known Activations