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. 9305
    Prev
    Next
    INDEX
    Explanations

    references to weapons, especially rocket launchers

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to 'launchers' in various contexts

    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
    Hart
    -0.67
    oddy
    -0.66
     Windsor
    -0.66
     Babe
    -0.65
    hum
    -0.65
     slavery
    -0.65
     Outs
    -0.64
     Detroit
    -0.63
    ribe
    -0.63
     Connecticut
    -0.63
    POSITIVE LOGITS
     launcher
    3.68
     launchers
    3.30
     Launcher
    3.12
    laun
    2.50
    Laun
    2.47
     Laun
    2.00
    launch
    1.62
     Launch
    1.59
    Launch
    1.48
     launches
    1.44
    Activations Density 0.026%

    No Known Activations