© 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. 1229
    Prev
    Next
    INDEX
    Explanations

    mentions of duration or time-related concepts, especially related to something no longer happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a cessation or end of a state or condition

    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
    NG
    -0.72
    é¾
    -0.68
     opposite
    -0.66
     Enhancement
    -0.66
    osite
    -0.65
    imov
    -0.64
    eer
    -0.63
    æĺ
    -0.62
    achev
    -0.62
    phen
    -0.61
    POSITIVE LOGITS
     tolerated
    0.91
     tolerate
    0.82
     bothering
    0.81
     bothered
    0.78
     reliant
    0.76
     relied
    0.75
     rely
    0.73
     able
    0.73
     viable
    0.72
     exists
    0.72
    Activations Density 0.049%

    No Known Activations