© 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. 18634
    Prev
    Next
    INDEX
    Explanations

    keywords related to guard duties and responsibilities

    oai_token-act-pair · gpt-3.5-turbo
    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
    theless
    -0.71
    lihood
    -0.71
    BLE
    -0.68
    MED
    -0.65
    CAST
    -0.63
    FORM
    -0.63
     Springs
    -0.62
    ãĥ£
    -0.62
    ctive
    -0.60
    issance
    -0.60
    POSITIVE LOGITS
    rail
    1.27
    iola
    1.02
    heed
    0.87
    maid
    0.86
    ians
    0.86
    tower
    0.83
    men
    0.83
     guarding
    0.82
    guard
    0.81
    pit
    0.81
    Activations Density 0.032%

    No Known Activations