© 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. 8-RES-JB
    11. 11540
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms, potentially related to a specific topic or field

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns associated with specific organizations, systems, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OHN
    -0.82
    abwe
    -0.81
    omez
    -0.76
    د
    -0.71
    qua
    -0.69
    yah
    -0.66
    Ó
    -0.66
    ع
    -0.66
    anchester
    -0.65
    «
    -0.65
    POSITIVE LOGITS
     itself
    0.72
     implementation
    0.70
     creation
    0.68
     members
    0.68
     package
    0.67
     module
    0.66
     duration
    0.66
     altogether
    0.65
     content
    0.65
     modules
    0.64
    Activations Density 0.479%

    No Known Activations