© 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. 3-RES-JB
    11. 23323
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Bertrand"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "rand" and its variants, as well as terms associated with measurements and references to quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.77
    ENTION
    -0.76
    anooga
    -0.75
    rious
    -0.73
    anto
    -0.70
    imoto
    -0.65
    intosh
    -0.63
    glers
    -0.63
    ISSION
    -0.63
    enzie
    -0.62
    POSITIVE LOGITS
    senal
    1.11
    angular
    0.90
    tery
    0.82
    haps
    0.75
    omial
    0.75
    ²¾
    0.74
    fect
    0.73
     Manz
    0.72
    ë
    0.71
    aceutical
    0.69
    Activations Density 0.025%

    No Known Activations