© 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. 3-RES-JB
    11. 13370
    Prev
    Next
    INDEX
    Explanations

    medical terms related to pelvic and abdominal regions

    oai_token-act-pair · gpt-3.5-turbo

    medical terminology related to anatomical structures and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -1.07
    HOU
    -0.88
    soDeliveryDate
    -0.83
     BaseType
    -0.83
    =-=-
    -0.77
    bringer
    -0.73
    mercial
    -0.68
     Flavoring
    -0.67
     CVE
    -0.66
     rarity
    -0.65
    POSITIVE LOGITS
     muscles
    0.96
    ysis
    0.96
    amina
    0.95
     lungs
    0.95
     gland
    0.95
     cortex
    0.95
     tissue
    0.92
     lobe
    0.92
     neurological
    0.91
     neurolog
    0.90
    Activations Density 0.247%

    No Known Activations