© 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. 2-RES-JB
    11. 1614
    Prev
    Next
    INDEX
    Explanations

    phrases that involve bookmarking or marking something for future reference

    oai_token-act-pair · gpt-3.5-turbo

    references to 'marks' or 'bookmarks' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADS
    -0.70
     circumstances
    -0.66
    FUL
    -0.64
    apist
    -0.63
     mishand
    -0.63
     subsystem
    -0.62
     mono
    -0.62
     reproductive
    -0.62
     pest
    -0.62
     agon
    -0.61
    POSITIVE LOGITS
    marks
    1.39
    mark
    1.36
    manship
    1.14
    emark
    1.07
    hyde
    0.98
    furt
    0.97
    eters
    0.94
    hof
    0.93
    marked
    0.90
    mast
    0.86
    Activations Density 0.010%

    No Known Activations