© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 11657
    Prev
    Next
    INDEX
    Explanations

    mentions of companies, organizations, and locations, particularly Foxconn and specific cities like Shenzhen and Jiang

    oai_token-act-pair · gpt-3.5-turbo

    references to specific corporate or organizational connections

    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
     Cy
    -0.69
    ONS
    -0.68
     Neb
    -0.68
     steroids
    -0.66
     Nar
    -0.65
     Lomb
    -0.64
     MAT
    -0.63
     Naz
    -0.62
     Ending
    -0.61
     Cum
    -0.60
    POSITIVE LOGITS
    conn
    1.16
    hao
    1.02
    acters
    0.81
    ibo
    0.81
    zhou
    0.78
    erie
    0.78
    pload
    0.76
    iets
    0.76
    idad
    0.76
     Jinping
    0.74
    Activations Density 0.008%

    No Known Activations