© 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. 6-RES-JB
    11. 13495
    Prev
    Next
    INDEX
    Explanations

    references to political entities and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to countries, political entities, and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partName
    -0.65
     âĢº
    -0.64
    Sym
    -0.64
    ãĥ£
    -0.61
    \":
    -0.59
     <<
    -0.58
    pmwiki
    -0.54
    rencies
    -0.53
    aj
    -0.52
     Morty
    -0.51
    POSITIVE LOGITS
     embassy
    0.64
    artney
    0.60
    ledged
    0.59
    erent
    0.57
    usalem
    0.57
     himself
    0.57
    agine
    0.56
     abroad
    0.56
    ensis
    0.56
    inges
    0.54
    Activations Density 0.733%

    No Known Activations