© 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. 7-RES-JB
    11. 1667
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various topics such as politics, economics, and entertainment

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or changes related to various topics, particularly in relation to "with" and its usage in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.75
    cause
    -0.65
    Others
    -0.65
    unless
    -0.63
    Benz
    -0.63
    ISON
    -0.63
    ARDS
    -0.62
    $.
    -0.62
    Cause
    -0.61
    ".[
    -0.61
    POSITIVE LOGITS
     hindsight
    0.79
    atile
    0.63
    ibrary
    0.62
     technically
    0.61
     polarized
    0.61
     democrat
    0.60
     actionGroup
    0.60
     nearing
    0.59
     modular
    0.59
     scarce
    0.58
    Activations Density 0.589%

    No Known Activations