© 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. 2-RES-JB
    11. 9220
    Prev
    Next
    INDEX
    Explanations

    the word "someone"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "someone."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interest
    -0.72
    èª
    -0.69
    ean
    -0.68
    heny
    -0.68
     Chain
    -0.68
    ories
    -0.63
    icons
    -0.62
    osterone
    -0.62
    de
    -0.60
    Dep
    -0.60
    POSITIVE LOGITS
     else
    1.41
    Else
    1.23
     Else
    0.86
    WithNo
    0.86
    else
    0.82
    20439
    0.81
     toget
    0.79
    etheless
    0.78
    ĪĴ
    0.78
     unlucky
    0.75
    Activations Density 0.022%

    No Known Activations