© 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. 9-RES-JB
    11. 15711
    Prev
    Next
    INDEX
    Explanations

    instances of words ending in '-ing'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe a type or kind of situation or phenomenon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wives
    -0.81
    ellen
    -0.79
     Signs
    -0.76
    ĸļ
    -0.75
     âĶľ
    -0.74
    ruary
    -0.74
    APS
    -0.74
    в
    -0.74
    ãĥĥãĥī
    -0.73
    aneers
    -0.72
    POSITIVE LOGITS
     thing
    1.43
     behavior
    1.03
     stuff
    1.00
     situation
    0.95
     mentality
    0.94
     endeavor
    0.94
     behaviour
    0.92
     attitude
    0.92
     shenan
    0.91
     activity
    0.89
    Activations Density 0.035%

    No Known Activations