© 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. 18878
    Prev
    Next
    INDEX
    Explanations

    terms related to medical equipment or procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical or health-related topics, specifically prosthetics and injuries

    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
    pires
    -0.62
    ĪĴ
    -0.57
    ggles
    -0.52
    annot
    -0.50
    pport
    -0.49
     warr
    -0.48
    ?).
    -0.45
    mand
    -0.45
     persists
    -0.45
    tains
    -0.44
    POSITIVE LOGITS
     yesterday
    0.76
     because
    0.72
     during
    0.72
     overnight
    0.65
    ,[
    0.64
    ;
    0.63
     while
    0.63
     whilst
    0.63
     shortly
    0.60
     insofar
    0.59
    Activations Density 1.224%

    No Known Activations