© 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. 11-RES-JB
    11. 4851
    Prev
    Next
    INDEX
    Explanations

    phrases related to software applications and functionalities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to functionalities or capabilities of applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ageddon
    -0.81
    Closure
    -0.75
    daq
    -0.75
    è¦ļéĨĴ
    -0.74
    ovember
    -0.70
    agate
    -0.70
    çİĭ
    -0.67
    assad
    -0.65
    ulture
    -0.64
    ãĥ´ãĤ¡
    -0.64
    POSITIVE LOGITS
     users
    1.64
     visitors
    1.36
     you
    1.33
     passers
    1.26
     developers
    1.23
     patrons
    1.23
     customers
    1.22
     guests
    1.22
     viewers
    1.21
     programmers
    1.19
    Activations Density 0.285%

    No Known Activations