© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21931
    Prev
    Next
    INDEX
    Explanations

    mentions of actions or situations involving neglect of safety or fairness in corporate settings

    oai_token-act-pair · gpt-3.5-turbo

    comparisons of corporate interests and employee welfare

    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
     Osw
    -0.78
     Lov
    -0.66
    iHUD
    -0.64
     Sync
    -0.62
    Split
    -0.62
    moil
    -0.61
     Archdemon
    -0.60
    ahime
    -0.60
     Reloaded
    -0.59
     Lenn
    -0.59
    POSITIVE LOGITS
     taxpayers
    0.96
     bribes
    0.96
     salaries
    0.91
     bureaucrats
    0.88
    their
    0.86
     taxpayer
    0.85
     legislatures
    0.85
     taxp
    0.84
     themselves
    0.83
     THEIR
    0.83
    Activations Density 0.858%

    No Known Activations