© 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. 17642
    Prev
    Next
    INDEX
    Explanations

    mentions of urban areas and population density

    oai_token-act-pair · gpt-3.5-turbo

    areas that are densely populated and their implications

    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
     omission
    -0.64
     Lifetime
    -0.57
    isman
    -0.54
    tein
    -0.54
    oyal
    -0.53
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.52
    ãĥīãĥ©
    -0.51
     Niet
    -0.50
    aughs
    -0.50
    erity
    -0.50
    POSITIVE LOGITS
     inhabited
    0.79
     neighborhoods
    0.72
     outskirts
    0.69
    insula
    0.67
     contiguous
    0.67
     gardens
    0.67
     populated
    0.67
     neighbourhoods
    0.66
     Ruins
    0.65
     periphery
    0.65
    Activations Density 1.273%

    No Known Activations