© 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. 8-RES-JB
    11. 1024
    Prev
    Next
    INDEX
    Explanations

    phrases involving a wide range or variety of items

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a wide range or variety of items or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lest
    -0.71
    uer
    -0.66
    pload
    -0.66
    xit
    -0.65
    head
    -0.64
    atown
    -0.64
     Quote
    -0.64
    arest
    -0.64
    ISTORY
    -0.63
    hest
    -0.63
    POSITIVE LOGITS
     disciplines
    1.11
     configurations
    1.11
     sorts
    1.09
     styles
    1.08
     viewpoints
    1.07
     perspectives
    1.05
     kinds
    1.05
     scenarios
    1.05
     formats
    1.04
     possibilities
    1.04
    Activations Density 0.102%

    No Known Activations