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

    Neuronpedia

    Jacobian LensNEW
    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. 13595
    Prev
    Next
    INDEX
    Explanations

    phrases related to replacement or substitution with something new

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to replacing old things with new alternatives

    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
    awar
    -0.71
    ibrary
    -0.65
    Plot
    -0.62
    TOR
    -0.61
    ipl
    -0.60
    verbal
    -0.60
    warn
    -0.59
    banks
    -0.57
    Words
    -0.57
    tip
    -0.56
    POSITIVE LOGITS
     newer
    1.37
     new
    1.19
     simpler
    1.06
     softer
    1.04
     cleaner
    1.02
     healthier
    0.98
     safer
    0.97
     nicer
    0.93
     brighter
    0.91
     modern
    0.90
    Activations Density 0.325%

    No Known Activations