© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 16065
    Prev
    Next
    INDEX
    Explanations

    locations associated with specific geographical areas or institutions

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vulner
    -0.65
     gag
    -0.59
     parach
    -0.58
    oteric
    -0.58
    ilater
    -0.58
     Izan
    -0.57
     sacrific
    -0.56
     medic
    -0.56
     cryptoc
    -0.55
     fuse
    -0.55
    POSITIVE LOGITS
    swick
    0.87
     Island
    0.77
    York
    0.75
    shaw
    0.73
    ria
    0.72
    rance
    0.71
    emouth
    0.71
    nton
    0.71
    mingham
    0.69
    gh
    0.68
    Activations Density 0.144%

    No Known Activations