© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13811
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific events or relationships

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases that indicate relationships or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Brexit
    -0.76
    advertising
    -0.74
    NVIDIA
    -0.73
    Netflix
    -0.72
    reprene
    -0.70
    ÄŁ
    -0.67
    iphate
    -0.67
    ribe
    -0.63
    tal
    -0.61
    merga
    -0.61
    POSITIVE LOGITS
     both
    1.22
     each
    0.97
     those
    0.93
     these
    0.93
     this
    0.91
     subsequent
    0.85
     the
    0.84
     either
    0.84
     theirs
    0.83
     whichever
    0.82
    Activations Density 0.761%

    No Known Activations