© 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. 4-RES-JB
    11. 16042
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to cooling systems and processes

    oai_token-act-pair · gpt-3.5-turbo

    references to cooling systems and technologies

    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
    tein
    -0.82
    ledged
    -0.74
    chu
    -0.70
    kie
    -0.69
    utan
    -0.68
    {"
    -0.67
     Binary
    -0.65
    chy
    -0.65
     NRS
    -0.64
     Breed
    -0.64
    POSITIVE LOGITS
     cooling
    1.03
     rack
    0.96
     cooled
    0.93
     cooker
    0.91
     racks
    0.90
     towers
    0.85
     cooler
    0.84
     exha
    0.82
     climates
    0.81
     sleeper
    0.80
    Activations Density 0.018%

    No Known Activations