© 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. 520
    Prev
    Next
    INDEX
    Explanations

    words related to locations or institutions, particularly those containing the term "Cent."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Cent" in various contexts

    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
    ãģ¦
    -0.78
    bye
    -0.69
    ãģŁ
    -0.68
    ãģł
    -0.66
    abulary
    -0.65
    owl
    -0.64
    oker
    -0.64
    ãģĹ
    -0.63
    lee
    -0.62
    NFL
    -0.61
    POSITIVE LOGITS
     Cent
    3.87
    Cent
    2.68
     cent
    2.18
     CENT
    1.92
    cent
    1.88
    CENT
    1.50
     Centre
    1.37
     Century
    1.26
     Centers
    1.19
     Cald
    1.18
    Activations Density 0.009%

    No Known Activations