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. 14138
    Prev
    Next
    INDEX
    Explanations

    words related to having a strong sense of imagination or foresight

    oai_token-act-pair · gpt-3.5-turbo

    references to "vision" 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
    mys
    -0.71
    gg
    -0.70
    ttle
    -0.68
    otte
    -0.68
    alter
    -0.64
     Holder
    -0.64
    STER
    -0.63
     Meier
    -0.62
    Random
    -0.62
    jo
    -0.62
    POSITIVE LOGITS
     vision
    3.94
     Vision
    2.60
     visions
    2.48
    Vision
    2.39
    vision
    2.03
     visionary
    1.62
     dream
    1.50
     blindness
    1.43
     dreams
    1.36
     sight
    1.33
    Activations Density 0.023%

    No Known Activations