© 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. 8-RES-JB
    11. 22592
    Prev
    Next
    INDEX
    Explanations

    names or words related to the Islamic State

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and terms related to specific organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bats
    -0.69
     Goose
    -0.66
     Zot
    -0.63
     behold
    -0.61
     myster
    -0.60
     Cardinals
    -0.59
     gum
    -0.58
     corrid
    -0.58
     lodge
    -0.57
     lith
    -0.57
    POSITIVE LOGITS
    iaz
    0.94
    ibo
    0.92
    agus
    0.88
    ream
    0.85
    orio
    0.83
    ippi
    0.81
    ãĤ¡
    0.78
    adic
    0.77
    chenko
    0.77
    opic
    0.76
    Activations Density 0.081%

    No Known Activations