© 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
    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. 388
    Prev
    Next
    INDEX
    Explanations

    the word "flurry" along with related words suggesting a sudden burst of activity or multiple occurrences happening rapidly

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sudden increases and decreases in activity or production

    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
     subordinates
    -0.74
     morally
    -0.74
     achievable
    -0.71
     transmitting
    -0.71
     mutants
    -0.66
    define
    -0.65
    ptr
    -0.65
    self
    -0.64
     depend
    -0.63
    ected
    -0.63
    POSITIVE LOGITS
     flurry
    2.52
     frenzy
    2.14
     uptick
    1.95
     spate
    1.91
     uproar
    1.80
     slump
    1.75
     outp
    1.74
     downturn
    1.68
     onslaught
    1.64
     lull
    1.64
    Activations Density 0.029%

    No Known Activations