© 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. 10190
    Prev
    Next
    INDEX
    Explanations

    words related to individuals named Carl

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Carl," indicating a focus on entities associated with that name

    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
    HER
    -0.76
     jihad
    -0.63
    rg
    -0.59
     Tycoon
    -0.59
    BLE
    -0.58
     normal
    -0.58
     gearing
    -0.58
     Blueprint
    -0.57
     watchdog
    -0.56
    req
    -0.54
    POSITIVE LOGITS
    isle
    1.64
    otta
    1.09
     Sagan
    1.07
    ito
    0.99
    ota
    0.96
    stadt
    0.95
    sen
    0.93
    obal
    0.92
    izabeth
    0.91
    ita
    0.90
    Activations Density 0.015%

    No Known Activations