© 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. 7843
    Prev
    Next
    INDEX
    Explanations

    phrases related to paying attention to small details or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to small, significant details or nuances

    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
    etheus
    -0.69
    ayn
    -0.67
    igion
    -0.63
    ogh
    -0.62
    åĭ
    -0.62
    chwitz
    -0.61
     Roses
    -0.61
    xit
    -0.60
    hovah
    -0.60
    oglu
    -0.59
    POSITIVE LOGITS
     (<
    1.22
    tiny
    1.08
     insignificant
    1.06
     increments
    0.93
     sized
    0.92
     tiny
    0.88
     smallest
    0.88
     manageable
    0.87
     tweaks
    0.86
     tucked
    0.84
    Activations Density 0.313%

    No Known Activations