© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 8549
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the brand "Siemens"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Siemens" and its derivatives, indicating a focus on references to the Siemens company and related topics

    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
    Thumbnail
    -0.72
     Juven
    -0.67
    ting
    -0.66
     Straw
    -0.64
     Kiw
    -0.62
     Hispanic
    -0.60
     Kushner
    -0.60
    stable
    -0.59
     chronological
    -0.59
     Trevor
    -0.59
    POSITIVE LOGITS
    iem
    1.21
    onday
    0.89
    ech
    0.88
    chwitz
    0.86
    zsche
    0.78
    umbai
    0.78
    omo
    0.78
    atis
    0.77
    eches
    0.76
    edience
    0.76
    Activations Density 0.007%

    No Known Activations