© 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. 10-RES-JB
    11. 10193
    Prev
    Next
    INDEX
    Explanations

    information related to creative works such as songs, videos, paintings, drawings, novels, or articles

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of media and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isEnabled
    -0.64
    addons
    -0.62
    ibles
    -0.62
    Methods
    -0.60
    ousands
    -0.59
     stadiums
    -0.58
    twitch
    -0.58
     Ports
    -0.58
    rawdownloadcloneembedreportprint
    -0.58
     Units
    -0.57
    POSITIVE LOGITS
     titled
    1.37
     featuring
    1.27
     depicting
    1.26
     entitled
    1.22
     wherein
    1.11
     involving
    1.09
     penned
    1.06
     narrated
    1.05
     illustrating
    1.05
     showcasing
    1.02
    Activations Density 0.391%

    No Known Activations