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. 23803
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases denoting something out of the ordinary or exceptional

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "extraordinary" or its variations

    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
     vs
    -0.71
    ader
    -0.70
    Link
    -0.69
     UI
    -0.68
    ink
    -0.67
     anyways
    -0.66
    rust
    -0.66
    Discuss
    -0.65
     Prev
    -0.62
    ware
    -0.62
    POSITIVE LOGITS
     extraordinary
    3.30
     exceptional
    2.16
     remarkable
    2.08
     incredible
    1.95
     astonishing
    1.90
     unusual
    1.82
     extraordinarily
    1.81
     unprecedented
    1.76
     astounding
    1.71
     unbelievable
    1.67
    Activations Density 0.015%

    No Known Activations