© 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. 7829
    Prev
    Next
    INDEX
    Explanations

    references to events or consequences that follow a significant incident

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in the wake of."

    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
    inates
    -0.68
    afort
    -0.68
     Conversation
    -0.64
    asse
    -0.61
    uana
    -0.60
    orsi
    -0.60
    ccording
    -0.59
    allo
    -0.56
    urat
    -0.56
     toget
    -0.55
    POSITIVE LOGITS
    math
    0.88
     of
    0.88
    fulness
    0.79
     thereof
    0.78
    storm
    0.69
    liest
    0.67
    ful
    0.65
    word
    0.64
    ward
    0.63
    mare
    0.63
    Activations Density 0.027%

    No Known Activations