© 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. 1875
    Prev
    Next
    INDEX
    Explanations

    words related to design aesthetics and physical space

    oai_token-act-pair · gpt-3.5-turbo

    significant nouns related to various types of situations or conditions

    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
    risome
    -0.80
    creen
    -0.75
    ervative
    -0.73
    ategory
    -0.72
    idden
    -0.72
    elcome
    -0.72
    icter
    -0.71
    ounding
    -0.71
    ritz
    -0.71
    licted
    -0.70
    POSITIVE LOGITS
    lets
    0.86
    naires
    0.84
     #
    0.84
    ages
    0.77
    ologies
    0.76
    backs
    0.73
     XXX
    0.72
    places
    0.71
    uses
    0.71
     holders
    0.71
    Activations Density 0.676%

    No Known Activations