© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7998
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "vast"

    oai_token-act-pair · gpt-3.5-turbo

    the word "vast" and its various uses in describing magnitude

    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
    isers
    -0.71
    face
    -0.70
    icide
    -0.68
    arsity
    -0.66
     Finally
    -0.65
    Finish
    -0.64
    gie
    -0.62
    imer
    -0.61
    cation
    -0.61
    osuke
    -0.60
    POSITIVE LOGITS
     vast
    3.43
     immense
    1.71
     enormous
    1.58
     overwhelming
    1.56
     huge
    1.49
     massive
    1.45
     sprawling
    1.43
     limitless
    1.40
     majority
    1.35
     gigantic
    1.35
    Activations Density 0.012%

    No Known Activations