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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 18894
    Prev
    Next
    INDEX
    Explanations

    the word "Jet" followed by a number indication

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Jet" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\\\\\\\\\\\\\
    -0.78
    orce
    -0.76
    ndum
    -0.72
     Parables
    -0.72
    skirts
    -0.69
    ãģį
    -0.68
    ACA
    -0.67
    \\\\\\\\
    -0.66
    ĻĤ
    -0.66
    Interstitial
    -0.66
    POSITIVE LOGITS
    Jet
    1.22
     Jet
    1.12
    jet
    0.92
     Airways
    0.90
    oleon
    0.76
    zeb
    0.73
     Ski
    0.72
     Polo
    0.69
     propulsion
    0.69
     Lines
    0.68
    Activations Density 0.008%

    No Known Activations