© 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. 9-RES-JB
    6. 7393
    Prev
    Next
    INDEX
    Explanations

    words related to personal names or titles, specifically in a formal or professional context

    oai_token-act-pair · gpt-3.5-turbo

    unique identifiers or names of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âĢº
    -0.63
     crumbling
    -0.59
     rundown
    -0.57
     polluted
    -0.57
     arenas
    -0.55
     overrun
    -0.55
     digest
    -0.54
     libraries
    -0.54
     founded
    -0.54
     Borders
    -0.54
    POSITIVE LOGITS
     whom
    0.99
     lieutenant
    0.94
    who
    0.93
    someone
    0.90
    ographer
    0.90
     secretaries
    0.88
    çͰ
    0.88
     spouse
    0.87
    omever
    0.87
    Lt
    0.86
    Activations Density 1.299%

    No Known Activations