© 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. 2-RES-JB
    11. 23924
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States or America

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.74
    volent
    -0.70
    ially
    -0.69
    ium
    -0.69
    -)
    -0.66
    ocyte
    -0.65
     penetration
    -0.63
    axis
    -0.62
     Gad
    -0.62
    ]-
    -0.61
    POSITIVE LOGITS
     Yemen
    0.60
     Chic
    0.60
     WHERE
    0.58
     POV
    0.58
     tigers
    0.58
    IGHTS
    0.58
     contempor
    0.57
    inki
    0.57
     Fisheries
    0.57
    tags
    0.56
    Activations Density 0.000%

    No Known Activations