© 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. 15621
    Prev
    Next
    INDEX
    Explanations

    links to articles or more information

    oai_token-act-pair · gpt-3.5-turbo

    repetitive structures or patterns in the text

    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
    bably
    -0.77
    beh
    -0.75
    viation
    -0.74
     arrang
    -0.74
     endeav
    -0.73
     persuasion
    -0.73
     foc
    -0.72
    eatures
    -0.71
    orate
    -0.70
    halla
    -0.70
    POSITIVE LOGITS
     Why
    1.16
     Latest
    1.15
     Recent
    1.04
     How
    1.03
     Inside
    1.03
     SHARES
    1.03
     VIDEOS
    1.02
     Could
    1.01
     Hundreds
    1.00
     Recap
    1.00
    Activations Density 0.054%

    No Known Activations