© 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. 0-RES-JB
    6. 2383
    Prev
    Next
    INDEX
    Explanations

    words related to cooling or temperature

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "cool" in various contexts

    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
     parity
    -0.71
     hinges
    -0.70
     bere
    -0.69
    aretz
    -0.69
    pel
    -0.68
     entangled
    -0.68
     meshes
    -0.67
     stumbling
    -0.66
     unp
    -0.65
    ramid
    -0.65
    POSITIVE LOGITS
     Cool
    3.71
    Cool
    2.72
    cool
    2.02
     cooler
    1.21
     Chill
    1.17
     cool
    1.11
     Quiet
    1.10
     Awesome
    1.08
     Cold
    1.07
     Jacket
    1.03
    Activations Density 0.016%

    No Known Activations