© 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. 7742
    Prev
    Next
    INDEX
    Explanations

    phrases related to paying tribute or honoring someone's memory

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Rest" and its variations in different contexts

    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
     Sapphire
    -0.66
    gee
    -0.63
     twins
    -0.62
     combination
    -0.59
     Centauri
    -0.57
     Blossom
    -0.56
     tong
    -0.56
    antha
    -0.55
    sha
    -0.54
     NEWS
    -0.54
    POSITIVE LOGITS
    raint
    1.49
    ructure
    1.49
    orative
    1.39
    raints
    1.36
    ricted
    1.34
    rained
    1.31
    aur
    1.29
    ruct
    1.27
    ricting
    1.25
    riction
    1.25
    Activations Density 0.028%

    No Known Activations