© 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. 23588
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, specifically names such as Sharon, Leah, and Denise

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly "Sharon" and other individuals

    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
    exempt
    -0.85
    notation
    -0.81
    rity
    -0.75
    effic
    -0.75
    ĻĤ
    -0.72
    credit
    -0.71
    safety
    -0.70
    nesota
    -0.70
    juven
    -0.69
    undai
    -0.69
    POSITIVE LOGITS
     Sharon
    0.96
     Levy
    0.92
     Blossom
    0.84
     Yard
    0.81
     Tate
    0.80
     Chev
    0.78
    ville
    0.78
     Angle
    0.76
     Katz
    0.76
     Richards
    0.75
    Activations Density 0.007%

    No Known Activations