© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10234
    Prev
    Next
    INDEX
    Explanations

    words ending in '-ed'

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ed" as suffixes, typically indicating past tense or related forms of verbs or adjectives

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ãĥ¯ãĥ³
    -0.65
    fruit
    -0.62
     Hebdo
    -0.61
    Story
    -0.60
     Kou
    -0.58
     Seat
    -0.57
    EStreamFrame
    -0.56
    sit
    -0.56
     Flask
    -0.56
    interface
    -0.55
    POSITIVE LOGITS
    uct
    1.31
    uctive
    1.26
    nesday
    1.25
    ict
    1.21
    monton
    1.17
    itors
    1.15
    icts
    1.13
    uce
    1.12
    ication
    1.12
    uction
    1.09
    Activations Density 0.066%

    No Known Activations