© 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. 9-RES-JB
    11. 18371
    Prev
    Next
    INDEX
    Explanations

    words related to a specific entity named "Hur"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Hur" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTE
    -0.77
    Leaks
    -0.71
    esthesia
    -0.71
    avers
    -0.70
    colo
    -0.66
    onymous
    -0.65
    emonic
    -0.65
     Chocobo
    -0.64
    ç¥ŀ
    -0.62
    ographical
    -0.61
    POSITIVE LOGITS
    ricane
    1.27
    rah
    1.04
    ricanes
    1.01
    witz
    0.96
    ley
    0.91
    ument
    0.87
    sts
    0.83
    mentation
    0.83
    oning
    0.82
    agement
    0.82
    Activations Density 0.080%

    No Known Activations