© 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. 10-RES-JB
    11. 3313
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles related to various forms of media such as books, music, and movies

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to various groups, projects, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exception
    -0.72
    onyms
    -0.70
    tops
    -0.69
    aneously
    -0.68
    ishment
    -0.68
    ress
    -0.67
    Äĩ
    -0.66
    istically
    -0.66
    iasis
    -0.65
    stadt
    -0.65
    POSITIVE LOGITS
    hift
    1.34
    pring
    1.29
    mith
    1.28
    peed
    1.25
    chool
    1.19
    hips
    1.19
    hip
    1.15
    pace
    1.13
    pread
    1.11
    kaya
    1.08
    Activations Density 0.211%

    No Known Activations