© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4869
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or proper nouns, particularly with aspects of science fiction, technology, or politics

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and entities

    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
     Committees
    -0.57
     Shutterstock
    -0.56
     unconstitutional
    -0.56
    soDeliveryDate
    -0.55
    selves
    -0.54
    */(
    -0.53
     acad
    -0.52
    externalActionCode
    -0.51
    uyomi
    -0.50
    ovie
    -0.49
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.58
    ÙĦ
    0.53
    İ
    0.53
    Rust
    0.52
    ®
    0.52
    Ŀ
    0.50
    Ö¼
    0.50
    ļé
    0.50
    prom
    0.49
     Isaac
    0.49
    Activations Density 0.762%

    No Known Activations