© 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. 7708
    Prev
    Next
    INDEX
    Explanations

    individuals or groups reporting instances of misconduct or abuse

    oai_token-act-pair · gpt-3.5-turbo

    instances of people coming forward to share their experiences or testimonies, often in a context of reporting misconduct

    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
     Directive
    -0.83
    Interstitial
    -0.72
     Designed
    -0.72
     goodbye
    -0.70
    natureconservancy
    -0.68
     guiIcon
    -0.65
     Regulations
    -0.64
     endif
    -0.63
     inferior
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.62
    POSITIVE LOGITS
     corrobor
    1.13
     alleging
    1.13
     allege
    1.10
     accuse
    1.07
     testify
    1.06
     attest
    1.04
     recount
    1.01
     allegations
    1.00
     accusing
    1.00
     testimonies
    0.99
    Activations Density 0.306%

    No Known Activations