© 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. 11593
    Prev
    Next
    INDEX
    Explanations

    a specific type of technical notation or abbreviation, such as chemical elements or programming languages and concepts

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations that refer to ratings, standards, or qualifications

    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
     Kub
    -0.74
     Leilan
    -0.70
     Subtle
    -0.67
    ĸļ
    -0.66
     Shak
    -0.65
     Dispatch
    -0.64
     Missing
    -0.64
     Raf
    -0.64
    quartered
    -0.64
     Yon
    -0.63
    POSITIVE LOGITS
    Ps
    1.22
    IDs
    1.18
    Vs
    1.10
    PO
    1.09
    Ms
    1.07
    Gs
    1.06
    TP
    1.05
    DI
    1.04
    BT
    1.04
    VR
    1.04
    Activations Density 0.174%

    No Known Activations