© 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. 8-RES-JB
    11. 3176
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and scientific research

    oai_token-act-pair · gpt-3.5-turbo

    negative physiological indicators or metrics related to health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guru
    -0.72
     Patriot
    -0.72
     Wiz
    -0.72
     perks
    -0.71
     nods
    -0.71
     Mama
    -0.69
     RBI
    -0.68
     Bes
    -0.68
     brunch
    -0.67
     Breed
    -0.67
    POSITIVE LOGITS
    derived
    1.22
    treated
    1.22
    negative
    1.21
    mediated
    1.18
    positive
    1.17
    response
    1.15
    biased
    1.15
    induced
    1.14
    containing
    1.13
    density
    1.12
    Activations Density 0.160%

    No Known Activations