Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 14638
    Prev
    Next
    INDEX
    Explanations

    superlatives used in comparisons related to different subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize superlatives and rankings across various categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •All the Features!

    No Comments

    Negative Logits
    lav
    -0.71
    actionDate
    -0.67
    dl
    -0.64
    potion
    -0.64
    plin
    -0.62
    itent
    -0.62
    velt
    -0.61
    sure
    -0.60
     unfocusedRange
    -0.60
    soft
    -0.59
    POSITIVE LOGITS
    ocating
    0.94
    igator
    0.88
     kinds
    0.87
    igators
    0.83
    udes
    0.80
     proportions
    0.76
     sorts
    0.75
    ogene
    0.73
    usions
    0.73
    uding
    0.71
    Activations Density 0.057%

    No Known Activations