Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14276
    Prev
    Next
    INDEX
    Explanations

    adjectives related to being crowded

    oai_token-act-pair · gpt-3.5-turbo

    the term "crowded" and related concepts indicating a lack of space or excessive occupancy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cia
    -0.68
    ods
    -0.68
    doc
    -0.67
    facts
    -0.66
     restore
    -0.66
    Notes
    -0.66
    UTH
    -0.65
    uci
    -0.65
    claim
    -0.63
     forgiveness
    -0.62
    POSITIVE LOGITS
     crowded
    3.67
     overcrowd
    2.15
     cramped
    1.95
     congest
    1.78
     crammed
    1.70
     bustling
    1.62
     packed
    1.58
     jammed
    1.53
     deserted
    1.46
     populated
    1.42
    Activations Density 0.027%

    No Known Activations