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. 8886
    Prev
    Next
    INDEX
    Explanations

    terms related to ballistic missiles

    oai_token-act-pair · gpt-3.5-turbo

    references to ballistic missile terminology

    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
     tentacles
    -0.70
     fishes
    -0.68
     appearances
    -0.67
     fish
    -0.66
     tort
    -0.64
     dresses
    -0.64
     gag
    -0.63
     slavery
    -0.63
     hex
    -0.62
     receptions
    -0.62
    POSITIVE LOGITS
    BM
    4.38
    bm
    1.91
     BM
    1.82
    BN
    1.55
    GM
    1.44
    DM
    1.44
    BT
    1.37
    BG
    1.37
    BP
    1.35
    JM
    1.34
    Activations Density 0.009%

    No Known Activations