© 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. 2-RES-JB
    11. 12432
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Social Security" with varied strengths of association

    oai_token-act-pair · gpt-3.5-turbo

    references to social security and related government programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.87
    phas
    -0.79
     Niet
    -0.77
    GMT
    -0.72
     Nile
    -0.70
    trop
    -0.69
    é¾įåĸļ士
    -0.66
     Lars
    -0.65
    à
    -0.65
    wcs
    -0.65
    POSITIVE LOGITS
     Advis
    0.98
     Administration
    0.89
     Security
    0.88
     Advisor
    0.86
     Assistance
    0.82
     Compensation
    0.81
     Checks
    0.80
    ratulations
    0.79
     Adviser
    0.78
    avorite
    0.77
    Activations Density 0.016%

    No Known Activations