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. 3-RES-JB
    6. 2598
    Prev
    Next
    INDEX
    Explanations

    specific ASCII characters

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uca
    -0.78
     hug
    -0.71
     frontline
    -0.70
     neighb
    -0.69
     mosqu
    -0.69
     undermin
    -0.67
     orchestr
    -0.67
     slam
    -0.67
     hust
    -0.66
     scrap
    -0.66
    POSITIVE LOGITS
    References
    1.14
    ³³³³
    1.09
    ³³³³³³³³
    1.09
    Thus
    1.08
    ³³³³³³³³³³³³³³³³
    1.06
    Chapter
    1.03
    Trivia
    1.01
    ³³³
    1.01
    However
    0.99
    Furthermore
    0.99
    Activations Density 0.985%

    No Known Activations