© 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. 12681
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a strong or powerful level of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "intense."

    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
    ware
    -0.70
     Libraries
    -0.70
    owe
    -0.69
    folk
    -0.66
    maid
    -0.65
    ule
    -0.65
    win
    -0.64
     stole
    -0.64
     Claim
    -0.64
    weed
    -0.63
    POSITIVE LOGITS
     intense
    3.14
     intensely
    1.96
     fierce
    1.93
     intensive
    1.80
     intensity
    1.75
     intensified
    1.64
     intens
    1.61
     vigorous
    1.55
     relentless
    1.49
     ferocious
    1.49
    Activations Density 0.019%

    No Known Activations