© 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. 20836
    Prev
    Next
    INDEX
    Explanations

    phrases related to trends or analyses thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to trends or changes over time

    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
    gur
    -0.94
    tein
    -0.75
     oath
    -0.73
    vette
    -0.69
     sacrific
    -0.63
    emies
    -0.62
     Lak
    -0.62
     dos
    -0.61
     straw
    -0.61
    ongh
    -0.61
    POSITIVE LOGITS
    setting
    1.27
     trend
    1.04
     Trend
    0.88
     toward
    0.87
     trends
    0.87
    chart
    0.85
    set
    0.82
     towards
    0.82
    Trend
    0.82
    line
    0.81
    Activations Density 0.033%

    No Known Activations