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. 14154
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences describing something as cool

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or admiration

    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
    olan
    -0.70
    ord
    -0.68
     Sinclair
    -0.65
     Estimates
    -0.63
    STER
    -0.62
     cited
    -0.62
    sters
    -0.62
     Destination
    -0.62
     Selection
    -0.61
    Repe
    -0.60
    POSITIVE LOGITS
     cool
    3.68
    cool
    2.53
     cooler
    2.29
    Cool
    2.20
     Cool
    2.15
     coolest
    2.15
     neat
    1.82
     cooled
    1.68
     cooling
    1.63
     chill
    1.49
    Activations Density 0.020%

    No Known Activations