© 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. 12418
    Prev
    Next
    INDEX
    Explanations

    dates and times related to sports events

    oai_token-act-pair · gpt-3.5-turbo

    specific time and date information related to events

    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
     handwriting
    -0.64
     flourished
    -0.63
     sworn
    -0.63
     bloom
    -0.61
     summ
    -0.61
     bearings
    -0.60
    ndra
    -0.59
     understatement
    -0.59
     acknowled
    -0.58
    abulary
    -0.58
    POSITIVE LOGITS
     ET
    1.10
    ESPN
    1.08
     PDT
    0.96
     PST
    0.96
     CST
    0.94
     EST
    0.88
    TV
    0.88
     PT
    0.87
     CT
    0.86
     EDT
    0.85
    Activations Density 0.084%

    No Known Activations