Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 10324
    Prev
    Next
    INDEX
    Explanations

    words related to cybersecurity and critical infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to critical infrastructure or security threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dest
    -0.70
     Lover
    -0.70
     Olive
    -0.68
     Commentary
    -0.66
     Evening
    -0.66
     Money
    -0.66
     Newsweek
    -0.66
     Pulitzer
    -0.66
     Living
    -0.65
     Conquest
    -0.64
    POSITIVE LOGITS
    GBT
    0.87
    ãĥ¼ãĥĨ
    0.75
    culosis
    0.75
    addons
    0.74
    zai
    0.74
    netflix
    0.70
    ibaba
    0.69
    yip
    0.68
    fleet
    0.68
    wcs
    0.67
    Activations Density 0.000%

    No Known Activations