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. 1-RES-JB
    6. 12766
    Prev
    Next
    INDEX
    Explanations

    mentions of the company "Airbus"

    oai_token-act-pair · gpt-3.5-turbo

    references to Airbus, including its various aircraft models and related information

    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
    hood
    -0.91
    ithing
    -0.71
    jay
    -0.69
    knife
    -0.69
    ħĭ
    -0.69
    nee
    -0.69
    lder
    -0.67
    ston
    -0.64
    friend
    -0.63
    Ķ
    -0.63
    POSITIVE LOGITS
     seiz
    0.93
     tyr
    0.92
    ratulations
    0.91
     Airbus
    0.86
     mathemat
    0.84
    bourg
    0.84
    inia
    0.83
    ensical
    0.79
     therap
    0.79
     contrace
    0.78
    Activations Density 0.010%

    No Known Activations