© 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. 18590
    Prev
    Next
    INDEX
    Explanations

    technology-related terms, particularly related to companies and products

    oai_token-act-pair · gpt-3.5-turbo

    references to technology companies and their market performance

    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
     poem
    -0.74
     forc
    -0.72
     Auschwitz
    -0.70
     inscribed
    -0.70
    constitutional
    -0.67
    opathic
    -0.67
     poems
    -0.66
    Allah
    -0.66
    yll
    -0.66
    accompanied
    -0.65
    POSITIVE LOGITS
     startups
    1.04
     lackluster
    1.03
     profitability
    1.01
     IPO
    1.00
     OEM
    0.97
     marketers
    0.97
     antitrust
    0.96
     competitors
    0.96
     CES
    0.95
     marketing
    0.95
    Activations Density 1.160%

    No Known Activations