© 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. 1-RES-JB
    6. 11435
    Prev
    Next
    INDEX
    Explanations

    the name "Cohen."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Cohen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enment
    -0.77
    Lex
    -0.75
    Anonymous
    -0.72
    ained
    -0.69
    self
    -0.67
    tub
    -0.66
    Self
    -0.65
    rha
    -0.65
    urities
    -0.64
     parole
    -0.64
    POSITIVE LOGITS
     Cohen
    0.97
    agher
    0.94
    ²¾
    0.87
    hiba
    0.77
    bach
    0.76
    wald
    0.75
     Horowitz
    0.73
    SHIP
    0.73
    bats
    0.72
     Coliseum
    0.69
    Activations Density 0.006%

    No Known Activations