© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12221
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "and", often in lists or conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating connections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idae
    -0.65
    illus
    -0.62
    ãĤ·ãĥ£
    -0.60
    ocrat
    -0.59
    ril
    -0.59
    ãĥ¼ãĥ
    -0.59
    >[
    -0.57
    ãĥĩãĤ£
    -0.57
    fif
    -0.56
    tip
    -0.56
    POSITIVE LOGITS
     elsewhere
    1.63
     abroad
    1.31
     throughout
    1.27
     across
    1.20
     in
    1.17
     within
    1.11
     on
    1.10
     beyond
    1.09
     anywhere
    1.09
     amongst
    1.08
    Activations Density 0.392%

    No Known Activations