© 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. 8-RES-JB
    11. 6199
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating a significant degree or extent

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers expressing significant or drastic change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifully
    -0.89
    sburgh
    -0.81
    afety
    -0.80
    elsen
    -0.75
    tein
    -0.75
    tale
    -0.73
     Memories
    -0.72
    awaru
    -0.67
    gerald
    -0.67
    plugin
    -0.66
    POSITIVE LOGITS
     impacted
    0.99
     impacting
    0.94
     reduce
    0.93
     reduces
    0.93
     effected
    0.92
     reduced
    0.90
     differ
    0.88
     altered
    0.87
     improves
    0.86
     improve
    0.84
    Activations Density 0.050%

    No Known Activations