© 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. 2-RES-JB
    11. 14109
    Prev
    Next
    INDEX
    Explanations

    mentions of specific vitamins

    oai_token-act-pair · gpt-3.5-turbo

    mentions of vitamins and their related health implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shore
    -0.78
    fm
    -0.77
    ker
    -0.77
    eh
    -0.73
    Topics
    -0.72
    speech
    -0.70
    pps
    -0.70
    eden
    -0.68
    */(
    -0.68
    cue
    -0.67
    POSITIVE LOGITS
     vitamin
    1.29
     vitamins
    1.25
     Vitamin
    1.22
    amins
    1.14
    ritional
    1.08
     nutrit
    0.96
    itamin
    0.90
    aceous
    0.90
     iodine
    0.89
     supplementation
    0.89
    Activations Density 0.011%

    No Known Activations