© 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. 20585
    Prev
    Next
    INDEX
    Explanations

    documents or information obtained through various means like FOIA requests or legal channels

    oai_token-act-pair · gpt-3.5-turbo

    references to documents that have been obtained through requests for information

    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
     preached
    -0.67
    apest
    -0.65
    psc
    -0.65
    enance
    -0.62
    Grade
    -0.62
     fixing
    -0.61
     hect
    -0.59
     <+
    -0.59
     doubled
    -0.58
    anguage
    -0.58
    POSITIVE LOGITS
     FOIA
    1.26
     Freedom
    1.22
     WikiLeaks
    1.19
     Wikileaks
    1.19
     whistleblower
    1.13
     whistlebl
    1.05
     whistleblowers
    1.01
     Snowden
    0.98
     disclosures
    0.95
     Privacy
    0.95
    Activations Density 0.212%

    No Known Activations