© 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. 9318
    Prev
    Next
    INDEX
    Explanations

    mentions of locations, specifically Palo Alto and Pueblo

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and cultural references

    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
    fully
    -0.75
    less
    -0.74
    hole
    -0.72
     Catalyst
    -0.70
    fulness
    -0.69
    henko
    -0.68
     spons
    -0.65
     VG
    -0.64
    mil
    -0.64
     IMAGES
    -0.63
    POSITIVE LOGITS
     Alto
    1.05
    ptions
    0.94
    atl
    0.77
    acan
    0.76
    unction
    0.76
    iries
    0.76
    pta
    0.75
    issance
    0.74
    ihu
    0.73
    alsh
    0.73
    Activations Density 0.051%

    No Known Activations