© 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. 0-RES-JB
    11. 2005
    Prev
    Next
    INDEX
    Explanations

    multi-word expressions that start with "Over"

    oai_token-act-pair · gpt-3.5-turbo

    phrases or patterns indicating an ongoing process or accumulation over time

    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
     thinking
    -0.65
     plat
    -0.63
     seal
    -0.62
     pudding
    -0.62
     writing
    -0.61
     propos
    -0.61
     prov
    -0.61
     special
    -0.59
     pretended
    -0.59
     spirit
    -0.59
    POSITIVE LOGITS
    Over
    3.33
     Over
    2.17
    OVER
    2.07
    over
    2.02
    overs
    1.72
     OVER
    1.66
    Around
    1.51
    Under
    1.49
    Through
    1.47
    Across
    1.44
    Activations Density 0.013%

    No Known Activations