© 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. 1-RES-JB
    11. 20528
    Prev
    Next
    INDEX
    Explanations

    instances of the word "standalone"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe independent or self-contained entities or systems

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    laus
    -0.76
    oras
    -0.72
    gor
    -0.72
    odor
    -0.71
    Age
    -0.69
    giene
    -0.69
    orio
    -0.69
    ordon
    -0.69
    Doctors
    -0.67
    ursed
    -0.67
    POSITIVE LOGITS
     standalone
    1.20
    alone
    0.96
    Buyable
    0.74
    icated
    0.74
    halla
    0.72
    BIL
    0.71
    inelli
    0.70
     foray
    0.68
     BAT
    0.68
    è»
    0.67
    Activations Density 0.006%

    No Known Activations