© 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. 20521
    Prev
    Next
    INDEX
    Explanations

    obligations or conditions related to a specific action or event

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and requirements related to events or actions

    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
    if
    -0.63
    ameless
    -0.62
    ²¾
    -0.61
    unless
    -0.60
     wonder
    -0.59
     wondered
    -0.58
    except
    -0.57
    almost
    -0.56
    DragonMagazine
    -0.55
     stemmed
    -0.55
    POSITIVE LOGITS
     sufficiently
    1.04
    .</
    0.96
     beforehand
    0.94
     enough
    0.91
     correctly
    0.89
     properly
    0.87
    .(
    0.86
    .
    0.82
    *.
    0.80
    .#
    0.79
    Activations Density 0.536%

    No Known Activations