© 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. 6-RES-JB
    11. 8536
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or buildings, such as churches, universities, and observatories

    oai_token-act-pair · gpt-3.5-turbo

    suffixed words related to various types of buildings or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enhagen
    -0.81
     carbohyd
    -0.74
    */(
    -0.73
    ãģĦ
    -0.66
    PUT
    -0.65
     polarized
    -0.63
    estamp
    -0.62
    icted
    -0.62
    è¦ļéĨĴ
    -0.61
    emic
    -0.61
    POSITIVE LOGITS
    lain
    0.91
     Royale
    0.87
    tyard
    0.82
    keeper
    0.76
     Plaza
    0.74
     âĵĺ
    0.74
    illery
    0.72
     Ruins
    0.71
     located
    0.71
     Hath
    0.71
    Activations Density 0.121%

    No Known Activations