© 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. 6-RES-JB
    11. 1484
    Prev
    Next
    INDEX
    Explanations

    conditional statements indicating potential future actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements, particularly those starting with "If."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Favorite
    -0.72
    Eye
    -0.69
    roid
    -0.68
    Í
    -0.66
     Deity
    -0.65
    LINE
    -0.65
    .�
    -0.64
    Rated
    -0.64
    ITED
    -0.62
    iliar
    -0.61
    POSITIVE LOGITS
     policymakers
    0.82
    fy
    0.76
    soever
    0.72
     elected
    0.71
     unchecked
    0.70
    llor
    0.69
    yip
    0.69
     negotiators
    0.68
    addock
    0.68
    rame
    0.67
    Activations Density 0.126%

    No Known Activations