© 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. 21636
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "did" in various forms and contexts

    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
    zai
    -0.65
    éĹĺ
    -0.61
     Shap
    -0.60
     Sleeping
    -0.59
    CRIP
    -0.58
     tension
    -0.57
     Scholar
    -0.56
     Penguin
    -0.55
     Koen
    -0.54
     Tayyip
    -0.53
    POSITIVE LOGITS
    ividual
    1.43
    rew
    1.09
    iversity
    1.04
    ynam
    0.99
    ependence
    0.99
    ynamic
    0.96
    ivers
    0.96
    iamond
    0.95
    iscover
    0.94
    iverse
    0.94
    Activations Density 0.022%

    No Known Activations