© 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. 1803
    Prev
    Next
    INDEX
    Explanations

    combinations of different elements or concepts to create something new

    oai_token-act-pair · gpt-3.5-turbo

    the word "with" in various contexts, indicating a focus on combination or partnership

    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
     alone
    -0.68
    stem
    -0.66
     overrun
    -0.65
    numbered
    -0.65
    chief
    -0.64
    itially
    -0.62
    ek
    -0.61
    Discuss
    -0.61
    sylvania
    -0.60
    pressure
    -0.59
    POSITIVE LOGITS
     impunity
    1.06
    stood
    0.98
     regard
    0.96
     regards
    0.90
    drawn
    0.84
     respect
    0.82
    trl
    0.71
    draw
    0.69
    EStreamFrame
    0.64
    soDeliveryDate
    0.62
    Activations Density 0.147%

    No Known Activations