© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2075
    Prev
    Next
    INDEX
    Explanations

    locations and geographical terms

    oai_token-act-pair · gpt-3.5-turbo

    locations and geographical references

    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
     Shia
    -0.94
    ollah
    -0.93
     Manziel
    -0.89
     Ruby
    -0.86
     Texans
    -0.84
     Mazda
    -0.82
    Michigan
    -0.82
    Ruby
    -0.82
     Astros
    -0.81
     Ranger
    -0.81
    POSITIVE LOGITS
     Amsterdam
    2.36
     Dutch
    2.32
     Netherlands
    2.31
    Dutch
    2.25
    ijn
    1.97
    ijk
    1.82
     Holland
    1.79
     Belgium
    1.61
     Ajax
    1.61
    sterdam
    1.58
    Activations Density 0.311%

    No Known Activations