© 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. 3-RES-JB
    11. 16066
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations and substances related to wellness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    encers
    -0.80
    doors
    -0.78
    ãģ¦
    -0.75
    esty
    -0.73
    tower
    -0.72
    osterone
    -0.71
    ility
    -0.70
    Oracle
    -0.69
    sonian
    -0.67
    encer
    -0.67
    POSITIVE LOGITS
     Alban
    1.15
     Albania
    1.11
     Kosovo
    0.96
    istani
    0.94
    istan
    0.91
     Airlines
    0.85
     Serbia
    0.83
     Tir
    0.82
     Ukrain
    0.81
     Lumpur
    0.80
    Activations Density 0.005%

    No Known Activations