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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18587
    Prev
    Next
    INDEX
    Explanations

    references to digital app stores

    oai_token-act-pair · gpt-3.5-turbo

    references to app stores, specifically the Apple App Store and its milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nir
    -0.81
    imum
    -0.75
    ortun
    -0.69
    aer
    -0.68
    vernment
    -0.68
    drawn
    -0.68
    tein
    -0.66
    icult
    -0.65
    rely
    -0.64
    emort
    -0.63
    POSITIVE LOGITS
     Store
    0.95
     Royale
    0.84
     shelves
    0.82
    front
    0.82
    store
    0.81
     Tycoon
    0.79
     Stores
    0.78
    DAQ
    0.78
     Depot
    0.76
    house
    0.74
    Activations Density 0.019%

    No Known Activations