Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6757
    Prev
    Next
    INDEX
    Explanations

    references to Getty Images

    oai_token-act-pair · gpt-3.5-turbo

    references to Getty Images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stood
    -0.84
     vain
    -0.73
     sediment
    -0.65
     fisherman
    -0.63
     flaw
    -0.62
     vac
    -0.62
    yip
    -0.62
     unreal
    -0.61
     bitters
    -0.61
    pired
    -0.61
    POSITIVE LOGITS
    sburg
    1.87
     Images
    1.34
    sburgh
    1.04
    Images
    0.93
    Film
    0.89
    images
    0.89
    photo
    0.87
    Accessory
    0.83
    Library
    0.80
    Track
    0.79
    Activations Density 0.008%

    No Known Activations