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. 0-RES-JB
    6. 6943
    Prev
    Next
    INDEX
    Explanations

    words related to advanced medical imaging techniques, specifically MRI (Magnetic Resonance Imaging)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical imaging technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Summoner
    -0.70
    blade
    -0.69
     turkey
    -0.66
     fandom
    -0.65
    uno
    -0.65
     sailor
    -0.63
    encer
    -0.62
     swell
    -0.61
    wow
    -0.59
    erity
    -0.59
    POSITIVE LOGITS
    enced
    3.87
    MRI
    1.35
    itored
    1.17
     MRI
    1.11
    ioned
    0.97
    gged
    0.84
     psychiat
    0.82
    ences
    0.82
    ence
    0.80
    ped
    0.78
    Activations Density 0.015%

    No Known Activations