© 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. 7-RES-JB
    11. 1639
    Prev
    Next
    INDEX
    Explanations

    phrases related to intensity or extent

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions that convey a sense of certainty or degree of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @@
    -0.63
    packages
    -0.61
     Chandra
    -0.58
     Takes
    -0.57
     Construct
    -0.55
    ++++++++++++++++
    -0.54
    casts
    -0.54
     ===
    -0.54
     Contributions
    -0.53
     UNCLASSIFIED
    -0.53
    POSITIVE LOGITS
     extent
    1.55
     detriment
    1.31
    venge
    1.19
     degree
    1.11
     fullest
    1.06
     tune
    0.98
     depths
    0.92
    merce
    0.84
     brink
    0.83
     ende
    0.80
    Activations Density 0.321%

    No Known Activations