© 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. 2-RES-JB
    11. 6640
    Prev
    Next
    INDEX
    Explanations

    specific mentions of locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic or physical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.84
    jin
    -0.77
    missions
    -0.77
    unes
    -0.76
    oug
    -0.74
    und
    -0.73
    aban
    -0.72
    gres
    -0.71
    kos
    -0.71
    rahim
    -0.68
    POSITIVE LOGITS
     location
    1.15
     locations
    1.13
     eater
    0.81
     locate
    0.77
     signage
    0.77
     locality
    0.75
     Locations
    0.74
     relocation
    0.74
    location
    0.74
     localization
    0.73
    Activations Density 0.019%

    No Known Activations