© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5693
    Prev
    Next
    INDEX
    Explanations

    references to the word "ature", which might be a common suffix or part of various words within the text

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of "nature."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Bey
    -0.69
    ista
    -0.65
    mel
    -0.64
    ãĤ®
    -0.64
    bring
    -0.62
    tons
    -0.61
    kn
    -0.61
    invoke
    -0.60
    Il
    -0.60
    Accessory
    -0.59
    POSITIVE LOGITS
    ature
    1.44
    atures
    1.07
     Dise
    0.86
    smanship
    0.75
    WARE
    0.75
     Thumbnails
    0.72
    ATURE
    0.72
    folios
    0.72
     Radius
    0.71
    entric
    0.70
    Activations Density 0.008%

    No Known Activations