© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11638
    Prev
    Next
    INDEX
    Explanations

    bits of code related to data processing and analysis

    oai_token-act-pair · gpt-3.5-turbo

    equality comparisons in code or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ldom
    -0.79
     Leban
    -0.71
    illet
    -0.70
    ¥ŀ
    -0.65
     oun
    -0.64
     coh
    -0.64
     Pratt
    -0.64
    auld
    -0.61
     sentence
    -0.61
     beg
    -0.61
    POSITIVE LOGITS
    [/
    0.87
    Downloadha
    0.75
    "},
    0.70
    ":["
    0.69
    iverse
    0.68
    fixed
    0.67
     Danger
    0.66
    reader
    0.65
    cards
    0.64
    "},{"
    0.64
    Activations Density 0.000%

    No Known Activations