© 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. 23045
    Prev
    Next
    INDEX
    Explanations

    terms related to politics and various industries, such as housing, healthcare, music, film, and marijuana

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political systems and structures

    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
     Kik
    -0.69
    tein
    -0.64
    oidal
    -0.61
    lihood
    -0.57
     clot
    -0.57
     cuff
    -0.56
     saline
    -0.56
    leys
    -0.56
    oret
    -0.55
     lambda
    -0.54
    POSITIVE LOGITS
     revolves
    0.88
    isine
    0.76
    âĢİ
    0.74
    ĸļ
    0.70
     âĶ
    0.67
    ography
    0.65
     circa
    0.64
    history
    0.64
     abroad
    0.64
     spanning
    0.64
    Activations Density 0.711%

    No Known Activations