© 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. 20542
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming, file formats, and technical instructions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to digital content creation and management

    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
     seriousness
    -0.77
    hillary
    -0.74
     lows
    -0.69
    sted
    -0.68
     reluctance
    -0.67
     affirmative
    -0.64
     abstinence
    -0.64
    ieth
    -0.64
     restrained
    -0.63
     declines
    -0.63
    POSITIVE LOGITS
     reuse
    1.10
     annot
    1.02
     downloadable
    1.01
     visualize
    1.00
     distribute
    0.99
     uploaded
    0.93
     upload
    0.93
     publish
    0.92
     embed
    0.91
     reproduce
    0.89
    Activations Density 0.386%

    No Known Activations