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. 18147
    Prev
    Next
    INDEX
    Explanations

    mentions of medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    references to statistics and data concerning health or safety

    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
    being
    -0.80
    boro
    -0.69
    minist
    -0.68
     Trog
    -0.65
    paces
    -0.62
    doors
    -0.57
    bag
    -0.56
    kees
    -0.56
    eco
    -0.56
    utical
    -0.56
    POSITIVE LOGITS
    Scroll
    1.06
    PHOTOS
    0.88
    Story
    0.76
    SPONSORED
    0.72
    Such
    0.68
    thinkable
    0.68
    Article
    0.65
    PROV
    0.65
    SEE
    0.65
     Related
    0.64
    Activations Density 0.421%

    No Known Activations