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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5316
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer processing capabilities and functions

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to technology and performance efficiency

    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
     Freddie
    -0.68
    fell
    -0.63
     blame
    -0.63
     Gilmore
    -0.58
     Leilan
    -0.57
    BuyableInstoreAndOnline
    -0.57
    interstitial
    -0.57
     Advis
    -0.56
     Roses
    -0.56
    CONCLUS
    -0.56
    POSITIVE LOGITS
     efficiently
    1.06
     seamlessly
    0.97
     cheaply
    0.96
     effortlessly
    0.96
     securely
    0.91
     convenient
    0.91
     uninterrupted
    0.90
     seamless
    0.89
     inexpensive
    0.88
     hassle
    0.87
    Activations Density 0.487%

    No Known Activations