© 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. 13986
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of presence or being in a specific location is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    the frequent use of the word "there" in various contexts

    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
     Warfare
    -0.65
     FTA
    -0.62
     appell
    -0.56
    IRE
    -0.55
    udeau
    -0.55
     Breach
    -0.55
     Fair
    -0.54
     Cum
    -0.54
    Americ
    -0.53
     Merge
    -0.53
    POSITIVE LOGITS
    abouts
    1.38
    tical
    1.11
    tics
    0.96
    fore
    0.96
    tic
    0.89
     somewhere
    0.88
    inel
    0.86
    upon
    0.81
    for
    0.75
     Somewhere
    0.75
    Activations Density 0.054%

    No Known Activations