© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12439
    Prev
    Next
    INDEX
    Explanations

    terms related to specific types of currency or monetary value

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "ral" or "ralis," likely referring to certain geographical or cultural classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     miser
    -0.74
     stub
    -0.68
     appe
    -0.66
     Att
    -0.64
     character
    -0.62
     characters
    -0.61
     stamp
    -0.59
     jugg
    -0.59
     intoler
    -0.59
     uncomp
    -0.58
    POSITIVE LOGITS
    ral
    4.75
    rals
    2.46
    RAL
    1.65
    ran
    1.39
    rum
    1.37
    ras
    1.37
    riel
    1.33
    ricular
    1.28
    rine
    1.26
    rium
    1.24
    Activations Density 0.019%

    No Known Activations