© 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. 1-RES-JB
    11. 11474
    Prev
    Next
    INDEX
    Explanations

    content-related terms, such as 'Content'

    oai_token-act-pair · gpt-3.5-turbo

    references to "content" in various contexts

    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
    rolet
    -0.83
     damn
    -0.69
     Scientology
    -0.68
     Rasmussen
    -0.66
    ipers
    -0.64
    Äĩ
    -0.64
    udeb
    -0.64
    Anonymous
    -0.63
     Soros
    -0.61
     Phi
    -0.60
    POSITIVE LOGITS
    Content
    1.22
     Content
    1.18
    content
    1.03
     content
    0.98
    edly
    0.90
    ngth
    0.79
     Contents
    0.78
    area
    0.78
    odox
    0.78
    inventoryQuantity
    0.74
    Activations Density 0.005%

    No Known Activations