© 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. 0-RES-JB
    11. 8297
    Prev
    Next
    INDEX
    Explanations

    file paths in a Unix-like format

    oai_token-act-pair · gpt-3.5-turbo

    segments of text that consist of URLs or file paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciating
    -0.69
    etheless
    -0.67
    iless
    -0.62
    DonaldTrump
    -0.57
    assetsadobe
    -0.54
    ifully
    -0.52
    aterasu
    -0.51
    footed
    -0.50
    ificent
    -0.50
    irteen
    -0.50
    POSITIVE LOGITS
    /
    2.75
    /_
    1.96
    /?
    1.72
    /)
    1.70
    /$
    1.70
    /,
    1.69
    /#
    1.68
    /"
    1.67
    /
    1.65
    /(
    1.64
    Activations Density 0.063%

    No Known Activations