© 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. 3-RES-JB
    11. 16350
    Prev
    Next
    INDEX
    Explanations

    the word "Someone" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to "someone"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heny
    -0.74
    interest
    -0.73
    ories
    -0.70
    èª
    -0.69
    osterone
    -0.68
     Chain
    -0.67
    lag
    -0.65
    ean
    -0.65
    inders
    -0.62
    esm
    -0.62
    POSITIVE LOGITS
     else
    1.52
    Else
    1.23
     Else
    0.93
    else
    0.87
    WithNo
    0.86
    20439
    0.83
    ĪĴ
    0.81
     toget
    0.76
    rency
    0.70
     snatched
    0.70
    Activations Density 0.027%

    No Known Activations