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. 2-RES-JB
    6. 19120
    Prev
    Next
    INDEX
    Explanations

    references to social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of media-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.82
     Aires
    -0.67
    ç
    -0.66
     vow
    -0.61
     crust
    -0.61
     bark
    -0.60
     ranged
    -0.59
     barking
    -0.59
    stood
    -0.58
     autonom
    -0.58
    POSITIVE LOGITS
    uploads
    1.02
    tenance
    0.95
    wiki
    0.92
    Images
    0.92
    img
    0.90
    gallery
    0.89
    Pic
    0.86
    henko
    0.86
    photos
    0.85
    media
    0.84
    Activations Density 0.040%

    No Known Activations