© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 4786
    Prev
    Next
    INDEX
    Explanations

    words related to news and political figures

    oai_token-act-pair · gpt-3.5-turbo

    patterns or elements related to media and law

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

    No Comments

    Negative Logits
    hement
    -0.76
    etheless
    -0.71
    ataka
    -0.69
    rays
    -0.64
    arer
    -0.62
    ensical
    -0.61
     Fisheries
    -0.61
     submar
    -0.61
    eatures
    -0.60
     commission
    -0.60
    POSITIVE LOGITS
    ccording
    0.91
    --------------------------------------------------------
    0.87
    ================
    0.87
    Copyright
    0.86
    +++
    0.84
    =-=-=-=-
    0.84
    --------------------------------
    0.84
    à¼
    0.82
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.82
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.81
    Activations Density 0.195%

    No Known Activations