© 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. 11-RES-JB
    11. 7552
    Prev
    Next
    INDEX
    Explanations

    large numerical values related to financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical values and their relationships in the context of events or demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exting
    -1.07
    Þ
    -1.07
     eleph
    -1.06
     pione
    -1.01
    ò
    -1.00
    aditional
    -0.94
    ß
    -0.93
    ThumbnailImage
    -0.92
    Ý
    -0.91
    ñ
    -0.90
    POSITIVE LOGITS
    000
    0.70
    00
    0.63
    slice
    0.60
    0002
    0.59
    Untitled
    0.59
    SpaceEngineers
    0.58
    wcsstore
    0.57
    0010
    0.55
    Course
    0.52
    istar
    0.52
    Activations Density 0.146%

    No Known Activations