© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2868
    Prev
    Next
    INDEX
    Explanations

    words related to products being placed on shelves for sale

    oai_token-act-pair · gpt-3.5-turbo

    references to shelves in various contexts

    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
    atta
    -0.88
    Po
    -0.64
     overt
    -0.63
    ata
    -0.63
     induced
    -0.63
    Ī
    -0.62
    ames
    -0.61
     Pun
    -0.60
     involved
    -0.60
     Immunity
    -0.59
    POSITIVE LOGITS
     shelves
    4.07
     shelf
    3.01
     shel
    1.81
     racks
    1.43
     drawer
    1.42
     fridge
    1.34
     cabinets
    1.31
     pedest
    1.25
     refrigerator
    1.23
     desks
    1.22
    Activations Density 0.014%

    No Known Activations