© 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. 7-RES-JB
    11. 5039
    Prev
    Next
    INDEX
    Explanations

    phrases related to presidents and their rankings or qualities

    oai_token-act-pair · gpt-3.5-turbo

    references to U.S. presidents, particularly their approval ratings and assessments of their performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.85
    Channel
    -0.72
    doors
    -0.69
    Net
    -0.67
     Dimension
    -0.63
    door
    -0.63
    Lake
    -0.63
    yrinth
    -0.62
    INGTON
    -0.62
     Levant
    -0.62
    POSITIVE LOGITS
    thood
    1.08
    hips
    0.96
    clinton
    0.92
    trump
    0.90
    omics
    0.88
    ially
    0.87
     presidency
    0.86
     elected
    0.84
     assassinated
    0.84
    manship
    0.79
    Activations Density 0.140%

    No Known Activations