© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7296
    Prev
    Next
    INDEX
    Explanations

    references to the United States military and international affairs

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the abbreviation "U.S." or references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Attribution
    -0.65
    izen
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.58
     ax
    -0.57
    ãĥ¢
    -0.56
    amaz
    -0.56
     proceeds
    -0.55
     HF
    -0.55
    illin
    -0.55
     {"
    -0.54
    POSITIVE LOGITS
    S
    1.06
     Nations
    0.90
    $.
    0.86
    Va
    0.83
     Soccer
    0.81
    N
    0.78
    CLASSIFIED
    0.76
    NAT
    0.76
     States
    0.70
    K
    0.70
    Activations Density 0.050%

    No Known Activations