© 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. 10-RES-JB
    11. 15968
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs related to quantity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate alternatives or additions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Strait
    -0.59
     Catal
    -0.59
     Systems
    -0.57
     Howard
    -0.57
     Draper
    -0.56
     Activ
    -0.56
     Hamm
    -0.55
     Block
    -0.54
     Diesel
    -0.54
     Engineers
    -0.53
    POSITIVE LOGITS
    azard
    0.96
    astically
    0.94
    entimes
    0.91
    amount
    0.91
    rely
    0.86
    mean
    0.79
    parable
    0.77
    haps
    0.76
    FORE
    0.76
    ought
    0.75
    Activations Density 0.159%

    No Known Activations