© 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. 8-RES-JB
    11. 17641
    Prev
    Next
    INDEX
    Explanations

    statements that express opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" followed by various nouns

    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
    Edit
    -0.83
    ioch
    -0.78
    mares
    -0.71
    items
    -0.69
    images
    -0.68
    aday
    -0.68
    Ub
    -0.65
    adding
    -0.64
    Age
    -0.64
     belts
    -0.64
    POSITIVE LOGITS
     hoax
    1.08
     legitimate
    1.05
     mistake
    1.04
     coincidence
    1.02
     ploy
    0.95
     nuisance
    0.93
    versive
    0.93
     viable
    0.89
     distraction
    0.89
     genuine
    0.89
    Activations Density 0.274%

    No Known Activations