© 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. 11-RES-JB
    11. 9501
    Prev
    Next
    INDEX
    Explanations

    terms related to being close-knit or tightly connected

    oai_token-act-pair · gpt-3.5-turbo

    the term "tight" and its variations related to physical closeness or constraints

    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
     Courage
    -0.74
     Maxwell
    -0.72
    APH
    -0.65
    ORGE
    -0.64
    xual
    -0.63
    ically
    -0.63
    udi
    -0.62
     Patty
    -0.62
     Ily
    -0.62
    terday
    -0.61
    POSITIVE LOGITS
    knit
    1.12
    nesses
    1.00
    ness
    0.96
     knit
    0.94
    ro
    0.94
    fitting
    0.91
     fitting
    0.90
    est
    0.87
     coupling
    0.86
    ens
    0.86
    Activations Density 0.065%

    No Known Activations