© 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. 10278
    Prev
    Next
    INDEX
    Explanations

    products or items associated with technology or gadgets

    oai_token-act-pair · gpt-3.5-turbo

    specific types of consumer products, particularly related to bikes, watches, and electronics

    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
    NetMessage
    -0.94
     ILCS
    -0.82
    vernment
    -0.82
    rawdownloadcloneembedreportprint
    -0.74
    itored
    -0.73
    skip
    -0.70
    ãģĨ
    -0.69
     Transcript
    -0.69
    lishes
    -0.68
    Interstitial
    -0.67
    POSITIVE LOGITS
     manufacturer
    1.16
    maker
    1.09
     prototypes
    1.06
     designer
    1.04
     maker
    1.03
     builder
    1.03
     prototype
    1.02
    builder
    1.00
     manufact
    0.99
     manufacturers
    0.98
    Activations Density 0.276%

    No Known Activations