© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3339
    Prev
    Next
    INDEX
    Explanations

    phrases related to successful or remarkable events, achievements, or moments in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the success or significance of events in a timeline

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orem
    -0.78
    inet
    -0.78
    aft
    -0.66
     answ
    -0.64
    éĸ
    -0.64
    aye
    -0.63
    }}}
    -0.63
     [+]
    -0.63
    yrics
    -0.61
    arent
    -0.61
    POSITIVE LOGITS
     tumultuous
    1.22
     dominated
    1.11
     turbulent
    1.10
     plagued
    1.03
     characterized
    1.01
     littered
    1.01
     rocky
    1.00
     riddled
    0.99
     filled
    0.97
     fraught
    0.96
    Activations Density 0.209%

    No Known Activations