© 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. 23329
    Prev
    Next
    INDEX
    Explanations

    characters and locations related to a specific entity named "Kroger"

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand Kroger and its executives

    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
     bamboo
    -0.73
     instructional
    -0.69
     cushion
    -0.67
     MIDI
    -0.66
     Island
    -0.65
     Hawaii
    -0.64
     Yosemite
    -0.63
     pearl
    -0.62
     Taiwanese
    -0.62
    ool
    -0.61
    POSITIVE LOGITS
     Kro
    3.91
     McCl
    1.71
     Pog
    1.14
     Kru
    1.14
     Lowe
    1.04
     Nissan
    0.99
     grocer
    0.98
     Ashley
    0.98
     Schr
    0.98
    fox
    0.97
    Activations Density 0.030%

    No Known Activations