© 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. 11-RES-JB
    11. 6992
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations, specifically focusing on places named San

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "San" with high frequency, indicating a focus on locations in San Francisco and nearby cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICS
    -0.76
     CPC
    -0.64
     prompt
    -0.62
    ICAL
    -0.62
     emot
    -0.61
    ï¸ı
    -0.61
     professionally
    -0.59
     ground
    -0.57
     serious
    -0.57
     homework
    -0.57
    POSITIVE LOGITS
     Francisco
    1.50
     Diego
    1.41
     Bernardino
    1.33
     Antonio
    1.20
     Jose
    1.17
    ctuary
    1.16
    ibel
    1.16
     Mate
    1.07
    Disk
    1.07
    itary
    1.06
    Activations Density 0.013%

    No Known Activations