© 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. 15611
    Prev
    Next
    INDEX
    Explanations

    the word "worth" with different contexts and variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "worth" or phrases indicating value

    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
     trap
    -0.70
     ar
    -0.67
     rest
    -0.66
     satellite
    -0.64
     movement
    -0.64
     environment
    -0.63
     other
    -0.61
     periodic
    -0.61
     move
    -0.61
     streaming
    -0.59
    POSITIVE LOGITS
    worth
    5.09
     Worth
    1.57
     worth
    1.38
    worthy
    1.37
    sworth
    1.22
    WOR
    1.11
    hurst
    1.04
    bury
    1.01
    Merit
    1.01
    ford
    1.00
    Activations Density 0.011%

    No Known Activations