© 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. 6-RES-JB
    11. 20384
    Prev
    Next
    INDEX
    Explanations

    medical and physiological terms related to hormone levels, appetite regulation, oxidative stress, and arterial function

    oai_token-act-pair · gpt-3.5-turbo

    aspects related to hormonal and physiological changes affecting health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iquette
    -0.95
    gets
    -0.76
    trap
    -0.76
     Franch
    -0.76
    chart
    -0.71
    Austral
    -0.71
    ç«
    -0.70
    steamapps
    -0.70
    cour
    -0.70
    Planet
    -0.69
    POSITIVE LOGITS
     serum
    1.10
     susceptibility
    1.05
     inflammation
    1.01
     endogenous
    1.00
     protein
    1.00
     lipid
    0.97
     dose
    0.96
     antioxidant
    0.96
     estrogen
    0.96
     LDL
    0.95
    Activations Density 0.168%

    No Known Activations