© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23429
    Prev
    Next
    INDEX
    Explanations

    mentions of economic austerity measures

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of austerity

    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
    ITNESS
    -1.00
    ergy
    -0.89
    nesota
    -0.84
    ************
    -0.79
    FU
    -0.76
    know
    -0.75
    tein
    -0.73
    Chicken
    -0.69
    ership
    -0.69
    ****************
    -0.69
    POSITIVE LOGITS
     austerity
    1.02
    usterity
    0.90
     Measures
    0.87
     measures
    0.85
     therap
    0.78
     repression
    0.77
     burd
    0.75
     regime
    0.74
     unlaw
    0.73
     crunch
    0.70
    Activations Density 0.008%

    No Known Activations