© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 8970
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "core."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "core" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TN
    -0.72
    ufact
    -0.70
    _-
    -0.68
    pmwiki
    -0.67
    ã
    -0.64
    paces
    -0.63
     Vehicles
    -0.63
    vernment
    -0.63
    hops
    -0.62
    OTO
    -0.62
    POSITIVE LOGITS
     core
    0.99
    core
    0.98
    xit
    0.88
    opsis
    0.83
    utils
    0.80
    stone
    0.80
    hole
    0.79
     essence
    0.79
    gebra
    0.75
    lig
    0.74
    Activations Density 0.013%

    No Known Activations