© 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. 8-RES-JB
    11. 17621
    Prev
    Next
    INDEX
    Explanations

    relationships between the US and other countries

    oai_token-act-pair · gpt-3.5-turbo

    references to collaborations between the US and other countries or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocious
    -0.71
     sag
    -0.65
    bole
    -0.65
    utenberg
    -0.65
     shif
    -0.63
    agnetic
    -0.63
     overd
    -0.62
     forks
    -0.60
     cig
    -0.60
     highs
    -0.59
    POSITIVE LOGITS
     USSR
    0.98
    SEA
    0.96
     Europe
    0.94
     Allies
    0.91
    EU
    0.89
    Europe
    0.89
    Mexico
    0.88
     Samoa
    0.86
    Canada
    0.85
     NATO
    0.85
    Activations Density 0.205%

    No Known Activations