© 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 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. 5625
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to Columbus

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Columbus and its associated entities

    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
    vana
    -0.96
    ding
    -0.86
    icide
    -0.84
    icides
    -0.82
     conflic
    -0.80
    req
    -0.79
    ishers
    -0.76
    rha
    -0.75
    itsu
    -0.75
    hered
    -0.75
    POSITIVE LOGITS
     Crew
    1.11
     Columbus
    1.04
     Dispatch
    0.90
     Pike
    0.85
     Circle
    0.79
     Heights
    0.76
    Crew
    0.74
     Day
    0.72
     Ohio
    0.68
     Brew
    0.67
    Activations Density 0.015%

    No Known Activations