© 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. 17446
    Prev
    Next
    INDEX
    Explanations

    locations and geographic features

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations and related terms

    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
    STD
    -0.74
    SIGN
    -0.59
    FBI
    -0.57
    Miller
    -0.55
     treadmill
    -0.55
     induct
    -0.54
     bandwagon
    -0.54
     hairc
    -0.54
    Larry
    -0.53
     executives
    -0.53
    POSITIVE LOGITS
     northeastern
    1.20
     northwestern
    1.19
     southeastern
    1.18
     provinces
    1.17
     southwestern
    1.17
     province
    1.15
     northern
    1.12
     Mongolia
    1.12
     Caucasus
    1.10
     Albania
    1.09
    Activations Density 0.642%

    No Known Activations