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. 4593
    Prev
    Next
    INDEX
    Explanations

    websites and social media platforms that information or content can be found

    oai_token-act-pair · gpt-3.5-turbo

    references to websites and online platforms

    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
    eur
    -0.68
    saw
    -0.66
     exerc
    -0.64
    emet
    -0.61
     sucker
    -0.59
     spect
    -0.59
    ã
    -0.58
    pher
    -0.57
     proport
    -0.57
     nerv
    -0.57
    POSITIVE LOGITS
    Magazine
    1.04
    Daily
    0.76
     newsletter
    0.75
     Opinion
    0.74
     Newsletter
    0.74
     Politics
    0.73
    Next
    0.73
    Politics
    0.71
    Week
    0.70
    Movie
    0.68
    Activations Density 0.122%

    No Known Activations