© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 9381
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location, in this case, a store

    oai_token-act-pair · gpt-3.5-turbo

    references to retail locations or stores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.76
     Drawing
    -0.75
    vernment
    -0.70
     Matters
    -0.67
     Adv
    -0.66
    ï¸ı
    -0.65
    SHIP
    -0.64
    drawn
    -0.60
     Caucus
    -0.60
     Instruments
    -0.60
    POSITIVE LOGITS
     store
    1.23
    store
    1.22
     stores
    1.04
    Tes
    1.02
     shelves
    1.02
    Store
    1.00
    stores
    0.98
    keeper
    0.87
     Store
    0.86
    ãĤ£
    0.86
    Activations Density 0.016%

    No Known Activations