© 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. 11-RES-JB
    11. 1878
    Prev
    Next
    INDEX
    Explanations

    verbs related to gaining, acquiring, or obtaining something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to acquisition or gaining

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.76
    azo
    -0.73
    heses
    -0.71
    alian
    -0.69
    iso
    -0.66
    rake
    -0.65
    opus
    -0.65
    agate
    -0.64
    dq
    -0.63
    sis
    -0.63
    POSITIVE LOGITS
     notoriety
    1.31
     traction
    1.28
     momentum
    1.10
     insight
    1.07
     access
    1.05
     prominence
    1.04
     renown
    1.03
     fame
    1.03
     popularity
    1.02
     ascend
    0.99
    Activations Density 0.096%

    No Known Activations