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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 7159
    Prev
    Next
    INDEX
    Explanations

    political and governmental terms related to different countries

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sites
    -1.01
    things
    -0.96
    redients
    -0.94
    units
    -0.93
    cases
    -0.93
    items
    -0.93
    scenes
    -0.88
    sheets
    -0.88
    andals
    -0.88
    dogs
    -0.88
    POSITIVE LOGITS
     solution
    1.23
     takeover
    1.16
     renaissance
    1.16
     foothold
    1.03
     resurgence
    1.02
     presence
    1.01
     mandate
    1.00
     rethink
    0.98
     presidency
    0.97
     agenda
    0.96
    Activations Density 0.337%

    No Known Activations