© 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. 9155
    Prev
    Next
    INDEX
    Explanations

    references to indoor and outdoor locations or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to outdoor and indoor activities or settings

    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
    lda
    -0.65
    sections
    -0.64
    inders
    -0.64
    nce
    -0.64
     artery
    -0.62
    acts
    -0.60
    gments
    -0.60
    nex
    -0.58
    ptic
    -0.58
    ptoms
    -0.58
    POSITIVE LOGITS
     outdoors
    1.09
     indoors
    0.99
    manship
    0.97
    creen
    0.94
    ModLoader
    0.86
    men
    0.85
    edIn
    0.82
    erness
    0.81
    smanship
    0.80
    ï¸
    0.79
    Activations Density 0.009%

    No Known Activations