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. 4-RES-JB
    6. 12809
    Prev
    Next
    INDEX
    Explanations

    words related to air quality or air-related activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to air and transportation control systems

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

    No Comments

    Negative Logits
     Goat
    -0.73
    ciples
    -0.73
    batch
    -0.71
    Anonymous
    -0.69
    $$$$
    -0.68
    {"
    -0.67
     Scale
    -0.65
     Cow
    -0.64
     Vec
    -0.63
    bush
    -0.63
    POSITIVE LOGITS
    imeters
    0.83
     destro
    0.79
    ftime
    0.76
    agos
    0.70
     adrenaline
    0.69
     humid
    0.68
     breat
    0.68
     respir
    0.67
    enko
    0.67
     conditioning
    0.66
    Activations Density 0.127%

    No Known Activations