© 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. 20318
    Prev
    Next
    INDEX
    Explanations

    words related to the musician and songwriter "Gibbons"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Gib"

    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
    ISTER
    -0.71
     Schumer
    -0.69
    cv
    -0.68
    Advertisements
    -0.66
    Interstitial
    -0.65
    Tea
    -0.65
    DNA
    -0.65
     FDA
    -0.64
    OHN
    -0.64
    >[
    -0.64
    POSITIVE LOGITS
     Gib
    0.99
    raltar
    0.98
    bler
    0.96
    bling
    0.96
    odies
    0.95
    undai
    0.94
    adish
    0.90
    aldi
    0.89
    bole
    0.89
    rets
    0.89
    Activations Density 0.004%

    No Known Activations