© 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. 23644
    Prev
    Next
    INDEX
    Explanations

    temporal references like dates, days of the week, and time-related words

    oai_token-act-pair · gpt-3.5-turbo

    temporal references such as time-related words and phrases

    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
    CRE
    -0.71
    toc
    -0.65
    ategy
    -0.60
    abase
    -0.60
    grave
    -0.58
    ĪĴ
    -0.58
     Tide
    -0.58
    andestine
    -0.58
    TY
    -0.57
     nonex
    -0.56
    POSITIVE LOGITS
    è£ħ
    0.80
    lier
    0.76
    grade
    0.69
    iven
    0.66
     Airways
    0.62
     rumours
    0.61
    ãĥŁ
    0.60
    nis
    0.60
    UFC
    0.59
     thicker
    0.59
    Activations Density 0.408%

    No Known Activations