© 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. 4365
    Prev
    Next
    INDEX
    Explanations

    dates in the format of a day and a year, such as "19th July 1960"

    oai_token-act-pair · gpt-3.5-turbo

    references to the 19th century

    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
    aminer
    -0.85
    orc
    -0.83
    anguage
    -0.75
    endum
    -0.74
    ensional
    -0.74
    orem
    -0.72
    arling
    -0.72
    ovie
    -0.72
    heed
    -0.69
    etitive
    -0.69
    POSITIVE LOGITS
    th
    1.00
    âĸĪâĸĪ
    0.93
    61
    0.81
    09
    0.81
    08
    0.81
    07
    0.80
    05
    0.80
    06
    0.79
    059
    0.79
    03
    0.78
    Activations Density 0.027%

    No Known Activations