© 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. 22473
    Prev
    Next
    INDEX
    Explanations

    geographical locations or regions

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing geographical locations and their characteristics

    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
     modifying
    -0.71
    illon
    -0.66
    Lear
    -0.64
    assin
    -0.62
     incremental
    -0.61
     Edited
    -0.60
    ayers
    -0.60
    cious
    -0.60
    thood
    -0.59
    pter
    -0.58
    POSITIVE LOGITS
     borders
    1.26
     lies
    1.21
     encompasses
    1.21
     contains
    1.15
     sits
    1.11
     neighb
    1.06
     boasts
    1.04
     attracts
    1.04
    population
    1.02
     comprises
    1.02
    Activations Density 0.271%

    No Known Activations