© 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. 7-RES-JB
    11. 23721
    Prev
    Next
    INDEX
    Explanations

    descriptions related to urban environments and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of busy urban environments and community interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çİĭ
    -0.67
     guiName
    -0.66
    ãģ®éŃĶ
    -0.62
    âĹ¼
    -0.61
    NAS
    -0.61
     Archdemon
    -0.59
     Wink
    -0.57
    èĢħ
    -0.57
    è£ħ
    -0.56
    qqa
    -0.55
    POSITIVE LOGITS
     spor
    0.63
     bounce
    0.58
     redund
    0.57
     ration
    0.57
     humidity
    0.56
     overhead
    0.55
     weave
    0.54
     liquids
    0.54
     layers
    0.54
     pores
    0.54
    Activations Density 1.888%

    No Known Activations