© 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. 2-RES-JB
    11. 12975
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to celestial bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to specific celestial bodies and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ned
    -0.87
    ited
    -0.80
    istical
    -0.76
    hedral
    -0.75
    IBLE
    -0.74
    istically
    -0.71
    utory
    -0.70
    isin
    -0.70
    govtrack
    -0.70
    arians
    -0.70
    POSITIVE LOGITS
    croft
    0.87
     Nile
    0.76
     Compan
    0.71
     Views
    0.71
    Trend
    0.66
     pige
    0.65
     Passage
    0.65
    gow
    0.65
     Contrast
    0.64
     Deter
    0.64
    Activations Density 0.020%

    No Known Activations