© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 22197
    Prev
    Next
    INDEX
    Explanations

    dates related to the year 1989

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the year 1989 and its mentions in various contexts

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

    No Comments

    Negative Logits
    istically
    -0.86
    istical
    -0.82
    arent
    -0.79
    iants
    -0.77
    holders
    -0.74
    ggies
    -0.73
    ndra
    -0.72
    antically
    -0.72
     Dare
    -0.71
    board
    -0.70
    POSITIVE LOGITS
    089
    0.87
    088
    0.86
    090
    0.86
    09
    0.82
    052
    0.82
    059
    0.80
    ÙĴ
    0.79
    terday
    0.78
    08
    0.76
    793
    0.76
    Activations Density 0.026%

    No Known Activations