© 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. 10387
    Prev
    Next
    INDEX
    Explanations

    numerical quantities or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "almost" to convey moderation or uncertainty

    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
    enter
    -0.68
     Apply
    -0.67
    nor
    -0.67
    pb
    -0.64
    ./
    -0.64
    ios
    -0.63
    rain
    -0.62
    topic
    -0.62
    osa
    -0.61
    )"
    -0.61
    POSITIVE LOGITS
     almost
    2.86
    almost
    2.35
     virtually
    2.07
     nearly
    2.00
     practically
    1.98
     Almost
    1.72
    Almost
    1.69
     scarcely
    1.65
     hardly
    1.58
     barely
    1.55
    Activations Density 0.025%

    No Known Activations