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. 11-RES-JB
    6. 7404
    Prev
    Next
    INDEX
    Explanations

    phrases related to fundraising activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation at the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥ŀ
    -0.70
     enthusi
    -0.70
     exha
    -0.69
     reluct
    -0.68
     unden
    -0.68
    jri
    -0.64
     unparalleled
    -0.62
     proport
    -0.61
     extensively
    -0.60
     destro
    -0.60
    POSITIVE LOGITS
     Either
    1.93
     Or
    1.86
    Either
    1.81
     Alternatively
    1.76
    Or
    1.75
     Whatever
    1.66
    Whatever
    1.55
     Regardless
    1.50
     Maybe
    1.47
     Perhaps
    1.35
    Activations Density 0.438%

    No Known Activations