© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4862
    Prev
    Next
    INDEX
    Explanations

    words related to crowded places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crowded" and related forms

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

    No Comments

    Negative Logits
    hum
    -0.79
    uracy
    -0.79
    rity
    -0.78
    ministic
    -0.73
    tymology
    -0.72
    istry
    -0.72
    arations
    -0.72
    clair
    -0.71
    shock
    -0.70
    alties
    -0.69
    POSITIVE LOGITS
     halls
    0.79
     queues
    0.76
     arenas
    0.74
     crowded
    0.73
     overcrowd
    0.70
     spaces
    0.68
     rooms
    0.66
    houses
    0.65
     seating
    0.64
     precincts
    0.64
    Activations Density 0.013%

    No Known Activations