© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12927
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical imaging techniques, specifically MRI (magnetic resonance imaging) scans

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical imaging techniques

    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
    coming
    -0.87
     Idle
    -0.86
    anza
    -0.75
    ãĥł
    -0.72
    orthy
    -0.71
    under
    -0.70
    ellation
    -0.68
    cake
    -0.68
    iston
    -0.68
    liam
    -0.67
    POSITIVE LOGITS
     scanners
    1.19
     scans
    1.15
     scanner
    1.11
    MRI
    1.09
     MRI
    1.02
     scan
    1.02
     Surgery
    0.93
     disse
    0.91
     imaging
    0.86
     scanning
    0.84
    Activations Density 0.011%

    No Known Activations