© 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. 0-RES-JB
    11. 8371
    Prev
    Next
    INDEX
    Explanations

    instances of the word "turning" in a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "turning."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geon
    -0.75
    Shares
    -0.70
    conom
    -0.70
     IMAGES
    -0.67
    Pool
    -0.66
    folio
    -0.65
    lements
    -0.65
    ress
    -0.63
    Includes
    -0.63
    aceae
    -0.63
    POSITIVE LOGITS
     turning
    3.23
     Turning
    2.18
    turn
    1.84
     turn
    1.74
     converting
    1.53
     transforming
    1.51
    Turn
    1.51
     turns
    1.50
     tipping
    1.49
     Turn
    1.41
    Activations Density 0.013%

    No Known Activations