© 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. 8-RES-JB
    11. 18454
    Prev
    Next
    INDEX
    Explanations

    mentions of minimum wage

    oai_token-act-pair · gpt-3.5-turbo

    mentions of minimum wage

    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
    riz
    -0.78
    encer
    -0.76
    uay
    -0.75
    rolog
    -0.75
    FORE
    -0.74
    alus
    -0.74
    kok
    -0.74
    herer
    -0.73
    ãĥĩ
    -0.71
    chu
    -0.69
    POSITIVE LOGITS
     wage
    1.17
     Wage
    0.96
     viable
    0.94
     amount
    0.93
     requirement
    0.90
     requirements
    0.88
     minimum
    0.86
     allowable
    0.84
     term
    0.81
    isite
    0.80
    Activations Density 0.024%

    No Known Activations