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. 707
    Prev
    Next
    INDEX
    Explanations

    words related to success in sports, specifically in American football terms

    oai_token-act-pair · gpt-3.5-turbo

    references to ups and downs, particularly in contexts of challenges and setbacks

    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
    ami
    -0.69
    âĢ
    -0.68
    î
    -0.63
    jad
    -0.61
     Ibn
    -0.60
    HOU
    -0.60
     Collection
    -0.60
    Obj
    -0.58
     Syndicate
    -0.58
    figure
    -0.58
    POSITIVE LOGITS
     downs
    4.30
     Downs
    2.19
    downs
    1.86
     ups
    1.41
    down
    1.38
     drawbacks
    1.36
    Down
    1.33
     downside
    1.27
     disadvantages
    1.25
     negatives
    1.21
    Activations Density 0.011%

    No Known Activations