Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17948
    Prev
    Next
    INDEX
    Explanations

    names of political figures and historical events related to Russia

    oai_token-act-pair · gpt-3.5-turbo

    references to historical and political figures related to Russian politics and Tibetan leaders

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

    No Comments

    Negative Logits
    OTT
    -0.73
    PASS
    -0.71
    TRY
    -0.69
     edge
    -0.68
    mination
    -0.67
    tes
    -0.67
    EEK
    -0.66
    AMD
    -0.64
     Grail
    -0.64
     crews
    -0.63
    POSITIVE LOGITS
     Jinping
    1.08
    cius
    0.92
    emort
    0.87
    itton
    0.83
    eus
    0.82
    DragonMagazine
    0.81
     Lavrov
    0.81
    ascus
    0.79
     Patriarch
    0.79
    sky
    0.78
    Activations Density 0.016%

    No Known Activations