© 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. 11551
    Prev
    Next
    INDEX
    Explanations

    locations or areas with the word "lounge" in them

    oai_token-act-pair · gpt-3.5-turbo

    mentions of lounges and related social spaces

    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
    UGC
    -0.73
    inventoryQuantity
    -0.71
    eded
    -0.69
    ãĥ¤
    -0.69
    displayText
    -0.69
     Uz
    -0.68
    âĵĺ
    -0.66
     ACTIONS
    -0.66
    ÑĮ
    -0.66
    Wan
    -0.64
    POSITIVE LOGITS
     lounge
    1.29
    ounge
    1.16
     Lounge
    1.09
    creen
    0.84
     chairs
    0.82
     lou
    0.80
    rette
    0.79
    room
    0.78
    stairs
    0.78
    halla
    0.76
    Activations Density 0.015%

    No Known Activations