© 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. 0-RES-JB
    11. 16446
    Prev
    Next
    INDEX
    Explanations

    mentions of the terrorist group Boko Haram

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ner
    -0.78
     Crow
    -0.72
     logs
    -0.70
    Driver
    -0.66
     priv
    -0.66
     Sto
    -0.64
     Wing
    -0.64
    sv
    -0.63
     Panzer
    -0.62
     throttle
    -0.62
    POSITIVE LOGITS
     Haram
    3.77
    ETH
    1.95
    vernment
    1.63
     Mons
    1.00
    OUS
    0.94
    arij
    0.87
    ESA
    0.87
    icol
    0.86
    aghd
    0.85
    merce
    0.84
    Activations Density 0.055%

    No Known Activations