© 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. 11-RES-JB
    11. 7058
    Prev
    Next
    INDEX
    Explanations

    words related to international or overseas activities

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical terms related to international and foreign contexts

    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
     resil
    -0.67
    eer
    -0.66
     Meter
    -0.62
    essee
    -0.62
    THER
    -0.58
     Peb
    -0.57
    nit
    -0.56
     Hamp
    -0.55
    nex
    -0.54
    ioxide
    -0.54
    POSITIVE LOGITS
    abouts
    0.95
    without
    0.87
     speaking
    0.83
    with
    0.82
     via
    0.79
     unnoticed
    0.76
    within
    0.72
    tics
    0.72
     without
    0.72
    selves
    0.72
    Activations Density 0.115%

    No Known Activations