© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6425
    Prev
    Next
    INDEX
    Explanations

    words related to financial austerity measures

    oai_token-act-pair · gpt-3.5-turbo

    references to austerity measures and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITNESS
    -0.93
    olulu
    -0.74
    ĸļ
    -0.74
    ividual
    -0.71
    aque
    -0.71
    ographs
    -0.70
    chester
    -0.69
    ĺħ
    -0.67
    leon
    -0.67
    nesota
    -0.67
    POSITIVE LOGITS
     austerity
    1.08
     measures
    1.06
     Measures
    1.03
    usterity
    0.91
     policies
    0.91
     reforms
    0.81
     cuts
    0.80
     programmes
    0.80
     bailout
    0.77
     budgets
    0.76
    Activations Density 0.055%

    No Known Activations