© 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. 15980
    Prev
    Next
    INDEX
    Explanations

    locations or places described in a waiting or anticipation context

    oai_token-act-pair · gpt-3.5-turbo

    instances of searching or looking for something specific

    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
     Polit
    -0.73
     Committee
    -0.71
     Subcommittee
    -0.71
     extensively
    -0.69
     Committees
    -0.68
    sted
    -0.67
     Ples
    -0.67
    misc
    -0.64
     numbering
    -0.63
     Edited
    -0.63
    POSITIVE LOGITS
     elusive
    1.23
     juicy
    1.06
     glimpse
    1.05
     goodies
    0.95
     tasty
    0.94
     savior
    0.93
     opportunity
    0.90
     scraps
    0.90
     payoff
    0.89
     snack
    0.89
    Activations Density 0.441%

    No Known Activations