© 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. 10-RES-JB
    11. 18665
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating degree or intensity, such as 'very' or 'incredibly'

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that emphasize the degree of an adjective or adverb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nexus
    -0.73
    orial
    -0.64
    irus
    -0.64
    ysical
    -0.63
    going
    -0.63
    izational
    -0.62
    psons
    -0.61
    isable
    -0.61
    ansk
    -0.59
    Posted
    -0.58
    POSITIVE LOGITS
     loudly
    1.37
     efficiently
    1.33
     aggressively
    1.32
     vigorously
    1.29
     harshly
    1.28
     closely
    1.27
     quickly
    1.27
     forcefully
    1.27
     smoothly
    1.25
     badly
    1.20
    Activations Density 0.153%

    No Known Activations