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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 12651
    Prev
    Next
    INDEX
    Explanations

    mentions of medical tests and procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical examinations and tests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    campaign
    -0.83
     piracy
    -0.82
    cair
    -0.76
     freel
    -0.76
    rising
    -0.74
     rebell
    -0.69
     DRM
    -0.67
    ateful
    -0.67
     indul
    -0.67
     Emacs
    -0.66
    POSITIVE LOGITS
    ysis
    1.16
     examination
    1.05
     autopsy
    1.04
     examinations
    1.02
    nsics
    0.98
     fluids
    0.95
    nsic
    0.94
     Examination
    0.93
     scan
    0.92
     forensic
    0.91
    Activations Density 0.316%

    No Known Activations