© 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. 3221
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "one of," indicating a superlative or comparison

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "one of" followed by a noun or group of nouns that signify significance or relevance

    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
    osponsors
    -0.79
    ittees
    -0.69
    ONS
    -0.66
    raid
    -0.64
    mons
    -0.64
    ples
    -0.63
    istance
    -0.63
     allot
    -0.62
    ption
    -0.62
    itures
    -0.61
    POSITIVE LOGITS
     Europe
    1.06
     America
    1.02
     Asia
    0.93
    America
    0.93
     humankind
    0.89
     Britain
    0.87
     Africa
    0.82
     mankind
    0.80
     Canada
    0.80
     humanity
    0.79
    Activations Density 0.078%

    No Known Activations