© 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. 10-RES-JB
    11. 6565
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographic locations like counties and towns

    oai_token-act-pair · gpt-3.5-turbo

    names of geographical locations or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sacrific
    -0.79
     penet
    -0.67
     organis
    -0.64
    advertisement
    -0.62
     inflamm
    -0.62
     opaque
    -0.62
    akable
    -0.62
    åĩ
    -0.61
     sabot
    -0.61
     compan
    -0.61
    POSITIVE LOGITS
    ville
    1.57
     Township
    1.55
     County
    1.51
     Heights
    1.46
    town
    1.32
     Hills
    1.30
    shire
    1.26
    stown
    1.25
    VILLE
    1.21
     Valley
    1.20
    Activations Density 0.193%

    No Known Activations