© 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. 16946
    Prev
    Next
    INDEX
    Explanations

    phrases related to data processing, analysis, and information sourcing

    oai_token-act-pair · gpt-3.5-turbo

    references to data collection and legal documentation

    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
    ¥µ
    -0.70
     exhilar
    -0.66
    bitious
    -0.59
     triumphant
    -0.59
     hugged
    -0.58
     passionately
    -0.58
     spectacle
    -0.56
     Chaser
    -0.56
     charismatic
    -0.56
     fiery
    -0.56
    POSITIVE LOGITS
     databases
    1.33
     database
    1.24
     FOIA
    1.14
     URLs
    1.11
     archives
    1.10
     dataset
    1.09
     verified
    1.08
     archive
    1.06
     anonym
    1.04
     redacted
    1.04
    Activations Density 1.094%

    No Known Activations