© 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. 10-RES-JB
    11. 5004
    Prev
    Next
    INDEX
    Explanations

    words related to definitions or defining something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "definition" and related terms

    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
    iddles
    -0.78
    ennes
    -0.74
    lication
    -0.72
    ADS
    -0.68
     Revelations
    -0.67
    liners
    -0.67
    loads
    -0.65
    ttes
    -0.65
    ÃĥÃĤ
    -0.64
    ramids
    -0.64
    POSITIVE LOGITS
     "
    1.16
     acceptable
    1.01
     '
    0.98
     insanity
    0.97
     "'
    0.97
     "-
    0.95
     permissible
    0.92
     "#
    0.89
     \"
    0.88
     "[
    0.87
    Activations Density 0.204%

    No Known Activations