© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 16159
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes or actions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions that indicate relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ade
    -0.61
    arch
    -0.60
    aida
    -0.57
    apolis
    -0.57
    ENTS
    -0.56
    ounters
    -0.55
     TBA
    -0.55
    aeda
    -0.55
    addafi
    -0.54
    opol
    -0.54
    POSITIVE LOGITS
     which
    2.27
    which
    1.90
     Which
    1.64
     whom
    1.59
    Which
    1.53
     whence
    1.41
     whose
    1.39
     wherein
    1.29
    whose
    1.21
     whereby
    1.08
    Activations Density 0.499%

    No Known Activations