© 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. 7765
    Prev
    Next
    INDEX
    Explanations

    words related to plants and nature

    oai_token-act-pair · gpt-3.5-turbo

    complex words or terms related to botanical or agricultural themes

    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
     balance
    -0.65
     HRC
    -0.60
     Spock
    -0.58
     combination
    -0.58
     focus
    -0.58
     colleg
    -0.57
     Dominion
    -0.55
     moderation
    -0.54
     rarity
    -0.54
     mitigation
    -0.53
    POSITIVE LOGITS
    ulhu
    0.87
    ornia
    0.76
    ioxide
    0.76
    CLE
    0.75
    oglu
    0.74
    Cola
    0.73
    ãĤ¼ãĤ¦ãĤ¹
    0.73
    aneous
    0.73
    anut
    0.72
    ascript
    0.71
    Activations Density 0.194%

    No Known Activations