© 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. 10-RES-JB
    11. 11365
    Prev
    Next
    INDEX
    Explanations

    terms related to design, development, and production processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to production and development processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leader
    -0.67
    verbs
    -0.65
    ¥µ
    -0.65
    enegger
    -0.63
    pants
    -0.61
    netflix
    -0.61
     Shades
    -0.60
    TextColor
    -0.60
    ocrates
    -0.59
    bold
    -0.59
    POSITIVE LOGITS
     process
    1.76
     processes
    1.31
     phase
    1.20
     workflow
    1.19
     phases
    1.15
     Process
    1.14
     stages
    1.14
     procedure
    1.09
     portion
    1.08
     procedures
    1.07
    Activations Density 0.355%

    No Known Activations