© 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. 6-RES-JB
    11. 13652
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a verb indicative of a temporary or permanent stoppage

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "for" followed by numbers, indicating durations or time frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illin
    -0.75
    quartered
    -0.71
    urred
    -0.67
    uckland
    -0.67
    ivil
    -0.66
    marine
    -0.65
    ryu
    -0.62
    mare
    -0.60
     approached
    -0.60
     outfit
    -0.58
    POSITIVE LOGITS
     awhile
    1.12
    geries
    1.11
     instance
    1.08
     example
    1.03
    WARD
    0.97
     eternity
    0.95
     purposes
    0.95
     months
    0.93
    gotten
    0.92
     starters
    0.90
    Activations Density 0.211%

    No Known Activations