© 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. 10553
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions happening concurrently with a specific time marker

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal pronouns and expressions of ongoing or past actions

    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
     occasion
    -0.75
     Cosponsors
    -0.74
    MpServer
    -0.74
    nexus
    -0.70
    ãĥ¼ãĥĨ
    -0.65
    ãĤ¨ãĥ«
    -0.65
     sooner
    -0.64
    EStream
    -0.61
     endpoint
    -0.61
     âĨij
    -0.60
    POSITIVE LOGITS
     await
    0.99
     waits
    0.94
     awaited
    0.94
     wait
    0.92
     awaits
    0.90
     waited
    0.86
     langu
    0.85
     sleeps
    0.83
     recovers
    0.82
     slept
    0.82
    Activations Density 0.160%

    No Known Activations