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. 8-RES-JB
    6. 14795
    Prev
    Next
    INDEX
    Explanations

    scientific journals where research studies are published

    oai_token-act-pair · gpt-3.5-turbo

    mentions of academic journals and their respective issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rises
    -0.72
     awoken
    -0.69
     brick
    -0.69
    UGH
    -0.66
    Lago
    -0.66
    iHUD
    -0.66
     barric
    -0.65
     awakening
    -0.65
     blight
    -0.64
    iak
    -0.64
    POSITIVE LOGITS
     Proceedings
    1.13
     Pediatrics
    1.09
     PLoS
    1.08
    ournals
    1.06
     journal
    0.96
     papers
    0.90
     PubMed
    0.89
     Nature
    0.87
     Papers
    0.85
     Editors
    0.85
    Activations Density 0.018%

    No Known Activations