© 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. 15993
    Prev
    Next
    INDEX
    Explanations

    names or terms related to shields

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "shield" in various contexts

    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
    iasco
    -0.78
    phrine
    -0.76
    gres
    -0.76
     âĸº
    -0.70
    pheus
    -0.69
    yles
    -0.69
    ribune
    -0.67
    lihood
    -0.67
    sequ
    -0.66
    orie
    -0.65
    POSITIVE LOGITS
    lain
    0.80
     absorbing
    0.79
    buster
    0.76
     shield
    0.75
     shields
    0.72
     Breach
    0.71
     erected
    0.71
     piercing
    0.67
     Breaker
    0.67
    wall
    0.67
    Activations Density 0.044%

    No Known Activations