© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22981
    Prev
    Next
    INDEX
    Explanations

    mentions of things being tightly filled or crowded, often related to physical spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being "packed" or filled with people, items, or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clair
    -0.75
    puter
    -0.74
    tymology
    -0.71
    recogn
    -0.68
    relation
    -0.68
    perature
    -0.68
    istry
    -0.68
    nesota
    -0.67
    pol
    -0.66
    relations
    -0.66
    POSITIVE LOGITS
    packed
    1.31
     packed
    0.97
     crates
    0.93
    arded
    0.90
     packs
    0.85
     loads
    0.85
     bundles
    0.82
     packing
    0.81
    arding
    0.77
    packs
    0.76
    Activations Density 0.008%

    No Known Activations