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. 6-RES-JB
    6. 7029
    Prev
    Next
    INDEX
    Explanations

    keywords related to space missions and rocket launches

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "launch" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icol
    -0.71
    Redd
    -0.70
    Flor
    -0.70
    redo
    -0.68
    tex
    -0.68
     Borders
    -0.68
    nton
    -0.67
    emo
    -0.65
    meric
    -0.65
    Score
    -0.65
    POSITIVE LOGITS
    lift
    0.89
    fleet
    0.89
     helicopters
    0.80
    pad
    0.80
    launch
    0.79
    eers
    0.78
     tubes
    0.77
     launching
    0.74
    nings
    0.73
    flight
    0.72
    Activations Density 0.027%

    No Known Activations