© 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. 11-RES-JB
    11. 20634
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or specifications

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ¯
    -0.74
     hers
    -0.72
     theirs
    -0.70
    actionDate
    -0.66
     ours
    -0.65
     Scourge
    -0.59
    ebin
    -0.58
    iterator
    -0.56
     affair
    -0.55
    plin
    -0.54
    POSITIVE LOGITS
     countries
    1.04
    th
    1.02
     different
    0.98
    nm
    0.95
    %-
    0.92
     languages
    0.91
    %
    0.89
     nations
    0.88
     Countries
    0.87
     categories
    0.86
    Activations Density 0.168%

    No Known Activations