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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 1435
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of defense in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "defense" and its related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolley
    -0.70
    zos
    -0.69
    oys
    -0.69
    vm
    -0.68
    ulla
    -0.68
    enny
    -0.68
    ibo
    -0.67
    zl
    -0.67
    orah
    -0.67
    liam
    -0.65
    POSITIVE LOGITS
     defense
    0.89
    Defense
    0.84
     Defense
    0.79
     defenses
    0.79
    defense
    0.77
     perimeter
    0.75
     defenders
    0.72
     defender
    0.71
    men
    0.70
     attorney
    0.70
    Activations Density 0.026%

    No Known Activations