© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9285
    Prev
    Next
    INDEX
    Explanations

    locations or businesses within a local community

    oai_token-act-pair · gpt-3.5-turbo

    references to local entities, locations, and community figures

    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
    obin
    -0.72
     infall
    -0.69
     analys
    -0.69
     invention
    -0.69
     cheat
    -0.65
     modification
    -0.65
     introdu
    -0.64
    emort
    -0.64
     disguise
    -0.64
     gadgets
    -0.63
    POSITIVE LOGITS
     Residents
    0.97
     borough
    0.93
     Parish
    0.91
     District
    0.87
     Borough
    0.87
     Prairie
    0.87
    Population
    0.86
    population
    0.85
     district
    0.82
    Residents
    0.82
    Activations Density 0.748%

    No Known Activations