© 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. 13010
    Prev
    Next
    INDEX
    Explanations

    words related to names, particularly "Bert."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific character names, particularly "Bert" and other related individuals

    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
    othal
    -0.77
     shore
    -0.70
     culturally
    -0.68
    phones
    -0.67
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.64
    esthetic
    -0.62
    gamer
    -0.61
    Effects
    -0.61
    assment
    -0.61
     mainland
    -0.61
    POSITIVE LOGITS
    rics
    1.11
     Bert
    1.03
    rand
    1.01
    ardo
    0.98
    ards
    0.89
    rique
    0.85
    ucci
    0.83
    ric
    0.82
    arded
    0.81
    olf
    0.81
    Activations Density 0.007%

    No Known Activations