© 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. 1-RES-JB
    11. 21038
    Prev
    Next
    INDEX
    Explanations

    verbs related to transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "become" that indicate change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atching
    -0.76
    aceous
    -0.70
    inarily
    -0.69
    otropic
    -0.68
    aging
    -0.65
     Glover
    -0.63
    ean
    -0.61
     Clock
    -0.61
     Hedge
    -0.60
     Hawkins
    -0.60
    POSITIVE LOGITS
     extinct
    0.87
    nces
    0.85
     entangled
    0.85
     accustomed
    0.79
    ãĤ£
    0.79
     embroiled
    0.76
     obsolete
    0.75
     increasingly
    0.73
     embr
    0.70
     CTR
    0.69
    Activations Density 0.027%

    No Known Activations