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. 0-RES-JB
    6. 6896
    Prev
    Next
    INDEX
    Explanations

    the word "ballistic" in various contexts, like ballistic missile, ballistic characteristics, and ballistic program

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ballistic missiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Place
    -0.68
     Gardens
    -0.67
     Feast
    -0.65
     Taste
    -0.65
    Fi
    -0.64
    Guest
    -0.63
     Garden
    -0.62
    cess
    -0.62
     Kop
    -0.62
    Pri
    -0.62
    POSITIVE LOGITS
     ballistic
    3.81
     Ballistic
    2.52
     missile
    1.57
     missiles
    1.40
     Missile
    1.29
     projectile
    1.19
     projectiles
    1.09
     rockets
    1.06
     bullet
    1.06
     thermal
    1.03
    Activations Density 0.008%

    No Known Activations