© 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. 0-RES-JB
    11. 1458
    Prev
    Next
    INDEX
    Explanations

    terms related to storage spaces, particularly closets

    oai_token-act-pair · gpt-3.5-turbo

    references to closets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pir
    -0.75
     Eid
    -0.71
    onso
    -0.68
    ó
    -0.65
    ribute
    -0.63
    Raw
    -0.63
     Rai
    -0.62
     Strikes
    -0.62
     Toll
    -0.62
    Ag
    -0.62
    POSITIVE LOGITS
     closet
    4.09
     wardrobe
    1.74
     clos
    1.59
     drawer
    1.53
     attic
    1.44
     suitcase
    1.32
     refrigerator
    1.29
     fridge
    1.29
     bedroom
    1.27
     locker
    1.24
    Activations Density 0.025%

    No Known Activations