© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18757
    Prev
    Next
    INDEX
    Explanations

    mentions of specific companies or organizations, particularly ones with the abbreviation "MS" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the entity "MS" and its related terms

    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
    rer
    -0.77
    rers
    -0.71
    rency
    -0.70
    framework
    -0.66
    footed
    -0.65
    redo
    -0.64
    rette
    -0.64
    taker
    -0.64
     provisional
    -0.64
     damned
    -0.62
    POSITIVE LOGITS
    RP
    1.34
    NBC
    1.18
    DN
    1.08
    DOS
    1.04
    gt
    1.01
    FT
    0.95
    AA
    0.94
    Cs
    0.93
    FW
    0.91
    VC
    0.88
    Activations Density 0.027%

    No Known Activations