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. 10-RES-JB
    6. 9760
    Prev
    Next
    INDEX
    Explanations

    issues of importance or concern

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alone
    -0.74
    ellow
    -0.70
    aimon
    -0.68
    gee
    -0.68
    isoft
    -0.64
    hew
    -0.64
    fledged
    -0.62
    ********
    -0.62
    ip
    -0.61
    pload
    -0.61
    POSITIVE LOGITS
     hardest
    1.54
     most
    1.50
     longest
    1.42
     greatest
    1.41
     heaviest
    1.40
     happiest
    1.35
     fastest
    1.31
     quickest
    1.31
     strongest
    1.31
     widest
    1.30
    Activations Density 0.417%

    No Known Activations