© 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. 11-RES-JB
    11. 5083
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geographical locations, particularly cities and countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Desk
    -0.77
    Lear
    -0.70
     Cutter
    -0.65
    reads
    -0.64
    ecycle
    -0.63
     Gloves
    -0.62
    enf
    -0.62
     Hermes
    -0.61
    inventoryQuantity
    -0.61
    ahon
    -0.61
    POSITIVE LOGITS
     populated
    1.42
     inhabited
    1.31
     situated
    1.27
     dotted
    1.25
     surrounded
    1.25
     overrun
    1.23
     nest
    1.18
     plagued
    1.13
     filled
    1.13
     riddled
    1.13
    Activations Density 0.307%

    No Known Activations