© 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 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. 16696
    Prev
    Next
    INDEX
    Explanations

    instances where the word "it" is used

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly "it" and "It," indicating a focus on subjects or objects in sentences

    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
     welcome
    -0.64
     paran
    -0.61
     Toast
    -0.60
     Liberty
    -0.59
     Wellington
    -0.59
     dexter
    -0.57
     Pax
    -0.57
     lifelong
    -0.57
     monopoly
    -0.57
     fugitive
    -0.57
    POSITIVE LOGITS
    âĢ
    1.65
    ÃĥÃĤ
    1.54
    «
    1.43
    âĶ
    1.36
    ãĢ
    1.35
    ¨
    1.34
    »
    1.30
    >>>>
    1.30
    âĺ
    1.29
    <<
    1.28
    Activations Density 0.332%

    No Known Activations