© 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 EvalsExportsinterp-engineNEWAPI 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. 11309
    Prev
    Next
    INDEX
    Explanations

    Punctuation marks and abbreviated terms related to people or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities denoted by initials or acronyms

    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
    jah
    -0.65
     Vulkan
    -0.61
    imore
    -0.57
    bett
    -0.57
     voices
    -0.55
    azeera
    -0.55
     Mara
    -0.55
     capsule
    -0.54
    ibrary
    -0.54
     Zed
    -0.53
    POSITIVE LOGITS
     Lovecraft
    0.88
    ongyang
    0.85
    ERSON
    0.80
    ivot
    0.80
    sylvania
    0.73
    ople
    0.70
    EED
    0.69
    erto
    0.68
    ĵĺ
    0.68
    essor
    0.68
    Activations Density 0.045%

    No Known Activations