© 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. 7819
    Prev
    Next
    INDEX
    Explanations

    verbs related to causing action or movement

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships and interactions involving individuals

    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
    Must
    -0.74
    VIDIA
    -0.62
     Tanz
    -0.61
    ifer
    -0.60
    idian
    -0.60
    could
    -0.59
     ESV
    -0.57
    oul
    -0.57
     betrayal
    -0.57
     rarity
    -0.57
    POSITIVE LOGITS
     acquainted
    1.21
     hooked
    1.20
     excited
    1.03
     addicted
    1.01
     interested
    1.00
     booted
    0.95
     accustomed
    0.95
     ready
    0.95
     pumped
    0.94
     into
    0.92
    Activations Density 0.119%

    No Known Activations