© 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. 6-RES-JB
    11. 15550
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and political activities involving those locations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations and their significance

    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
     reviewers
    -0.77
    PLIED
    -0.72
     testers
    -0.71
     pedals
    -0.70
     WARRANT
    -0.70
     exec
    -0.69
     RPM
    -0.68
    practice
    -0.66
     reviewer
    -0.65
     device
    -0.63
    POSITIVE LOGITS
     inhabited
    1.20
     neighbouring
    1.12
     inhabitants
    1.11
     farmland
    1.07
     annexed
    1.07
    population
    1.04
     mountainous
    1.04
     borders
    1.03
     UNESCO
    1.03
     adjoining
    1.01
    Activations Density 0.783%

    No Known Activations