© 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. 2-RES-JB
    6. 18645
    Prev
    Next
    INDEX
    Explanations

    words related to a hierarchical transition or inheritance of power or status

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities that hold or will hold positions of authority or leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cascade
    -0.73
    avery
    -0.71
    bra
    -0.68
     Spa
    -0.68
     Oval
    -0.68
     Honolulu
    -0.67
     Lange
    -0.67
    hma
    -0.66
     Belg
    -0.65
     Coulter
    -0.65
    POSITIVE LOGITS
     successor
    1.27
     successors
    1.04
     predecessor
    0.91
     therap
    0.85
     contender
    0.83
     predecessors
    0.81
     strugg
    0.81
     competitor
    0.76
    oleon
    0.75
    etheless
    0.75
    Activations Density 0.006%

    No Known Activations