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. 8-RES-JB
    6. 21210
    Prev
    Next
    INDEX
    Explanations

    superlatives and adjectives suggesting exceptional qualities or rankings

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating superlative qualities or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pection
    -0.79
    iances
    -0.74
    å§
    -0.72
    ALT
    -0.72
    APD
    -0.68
    bg
    -0.67
     appears
    -0.66
    iations
    -0.65
    hoe
    -0.65
    asonry
    -0.63
    POSITIVE LOGITS
     hardest
    1.32
     coolest
    1.30
     toughest
    1.28
     smartest
    1.26
     greatest
    1.25
     strongest
    1.25
     simplest
    1.24
     biggest
    1.22
     hottest
    1.21
     strang
    1.19
    Activations Density 0.147%

    No Known Activations