© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 22013
    Prev
    Next
    INDEX
    Explanations

    mentions of movement or relocation of people across borders or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to refugees and their journeys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Balanced
    -0.67
    pun
    -0.67
    rarily
    -0.66
    ãĤ´
    -0.65
    ĸļ
    -0.63
     incent
    -0.62
    emin
    -0.62
    anked
    -0.62
    lished
    -0.61
    advertising
    -0.61
    POSITIVE LOGITS
     flee
    1.44
     migrate
    1.34
     disembark
    1.31
     evacuate
    1.27
     relocate
    1.24
     return
    1.17
     leave
    1.16
     fled
    1.12
     lodge
    1.12
     depart
    1.11
    Activations Density 0.257%

    No Known Activations