© 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. 17693
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Dubai" along with a few variations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Dubai and related terms

    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
    urgical
    -0.82
    essee
    -0.81
    istics
    -0.80
    urgy
    -0.80
    istic
    -0.78
    eries
    -0.77
    fig
    -0.77
    otin
    -0.77
    anza
    -0.77
     Lovecraft
    -0.73
    POSITIVE LOGITS
     Dhabi
    1.07
     Emir
    0.94
    querque
    0.89
     Dubai
    0.81
     Emirates
    0.80
     Lumpur
    0.76
    doms
    0.75
    ilitation
    0.74
     UAE
    0.72
    enture
    0.72
    Activations Density 0.025%

    No Known Activations