© 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. 11-RES-JB
    11. 20653
    Prev
    Next
    INDEX
    Explanations

    phrases related to time durations or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to duration or time taken for processes

    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
     Trees
    -0.68
    Road
    -0.67
    psey
    -0.67
    ionic
    -0.67
    Haunted
    -0.66
    luaj
    -0.65
    patrick
    -0.64
    mini
    -0.64
    EngineDebug
    -0.63
    Champ
    -0.62
    POSITIVE LOGITS
     precedence
    1.27
     advantage
    1.26
     care
    1.08
     place
    1.07
    aways
    1.00
     pains
    0.93
     cues
    0.89
     awhile
    0.86
     priority
    0.86
     approximately
    0.82
    Activations Density 0.071%

    No Known Activations