© 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. 4-RES-JB
    11. 10201
    Prev
    Next
    INDEX
    Explanations

    references to retail stores

    oai_token-act-pair · gpt-3.5-turbo

    references to stores

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

    No Comments

    Negative Logits
    vous
    -0.81
    vernment
    -0.76
    SHIP
    -0.71
     Caucus
    -0.70
    ersen
    -0.69
    theless
    -0.69
    etheless
    -0.69
    ï¸ı
    -0.66
     Drawing
    -0.63
    laus
    -0.62
    POSITIVE LOGITS
     shelves
    1.19
    store
    1.09
     store
    1.06
    stores
    1.02
    houses
    1.02
     stores
    1.00
     storefront
    0.91
    keepers
    0.90
    rooms
    0.90
     malls
    0.88
    Activations Density 0.021%

    No Known Activations