© 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. 3205
    Prev
    Next
    INDEX
    Explanations

    words related to specific chemical elements, especially those ending in -ium

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various chemical elements, specifically those ending in "ium."

    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
    soDeliveryDate
    -1.16
     PsyNet
    -0.82
    things
    -0.75
    neys
    -0.74
    ãģ¦
    -0.74
    nee
    -0.74
    ãĥ¯ãĥ³
    -0.74
    stories
    -0.70
    abases
    -0.70
    eway
    -0.68
    POSITIVE LOGITS
     tremend
    1.37
     chloride
    1.09
     oxide
    0.90
    osate
    0.86
    s
    0.83
     trem
    0.80
     arsen
    0.79
     dioxide
    0.74
    ysis
    0.74
     salts
    0.74
    Activations Density 0.042%

    No Known Activations