© 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. 7-RES-JB
    11. 23734
    Prev
    Next
    INDEX
    Explanations

    specific dates and time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    elements of time and setting in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    notations
    -0.80
     thinner
    -0.68
    icons
    -0.66
    inventoryQuantity
    -0.65
     guarantees
    -0.64
     appreciated
    -0.62
     shred
    -0.61
     meanings
    -0.61
     emph
    -0.61
    ignt
    -0.61
    POSITIVE LOGITS
     Suppose
    0.80
     Plaintiff
    0.76
    EGIN
    0.76
     awoke
    0.76
    ezvous
    0.73
     Suddenly
    0.71
     approached
    0.70
     brainstorm
    0.69
     woke
    0.69
     awoken
    0.68
    Activations Density 1.241%

    No Known Activations