© 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. 11-RES-JB
    11. 15008
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning or resuming activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "back" indicating a return or復帰

    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
     sudden
    -0.62
     background
    -0.61
     Sorceress
    -0.61
     pall
    -0.60
     inacc
    -0.59
     unintended
    -0.56
     regard
    -0.56
     Conrad
    -0.56
     chain
    -0.55
    uary
    -0.55
    POSITIVE LOGITS
    tracking
    1.26
    ped
    1.18
    stab
    1.13
    packing
    1.06
    packs
    1.03
    lit
    1.01
    dro
    1.00
    dated
    1.00
    track
    0.99
    dating
    0.97
    Activations Density 0.044%

    No Known Activations