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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 8459
    Prev
    Next
    INDEX
    Explanations

    medical professionals and their titles

    oai_token-act-pair · gpt-3.5-turbo

    names and titles of medical professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bumper
    -0.71
     ponies
    -0.68
     twists
    -0.67
     outlets
    -0.65
     gor
    -0.62
     labels
    -0.62
     proxies
    -0.60
     stories
    -0.60
     compilation
    -0.59
     lev
    -0.59
    POSITIVE LOGITS
    .,
    0.95
    .;
    0.85
    uably
    0.81
    Assistant
    0.79
    ociate
    0.74
    NP
    0.74
    icably
    0.72
    VM
    0.71
    join
    0.71
     PhD
    0.71
    Activations Density 0.091%

    No Known Activations