© 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. 11-RES-JB
    11. 9488
    Prev
    Next
    INDEX
    Explanations

    nutrients such as vitamins, minerals, and proteins

    oai_token-act-pair · gpt-3.5-turbo

    references to various vitamins and their nutritional significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.73
    stem
    -0.72
    fm
    -0.70
    sing
    -0.69
    hou
    -0.67
    bare
    -0.65
    perture
    -0.65
    eh
    -0.64
    shr
    -0.64
    ttle
    -0.63
    POSITIVE LOGITS
     supplements
    1.12
    amins
    1.09
    rients
    1.06
     vitamins
    1.03
     supplementation
    1.01
     deficiencies
    1.00
     defic
    0.99
     nutrit
    0.98
     nutrients
    0.97
     vitamin
    0.96
    Activations Density 0.034%

    No Known Activations