© 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. 9-RES-JB
    11. 7528
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic inflation

    oai_token-act-pair · gpt-3.5-turbo

    references to inflation and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.91
    ¯¯¯¯¯¯¯¯
    -0.71
     Privacy
    -0.70
    ////////
    -0.69
    ¯¯¯¯
    -0.68
     Duel
    -0.66
     DU
    -0.66
    WAYS
    -0.63
     DAC
    -0.63
     LAN
    -0.62
    POSITIVE LOGITS
    ary
    1.30
    adjusted
    1.01
    arily
    0.93
     rates
    0.92
    flation
    0.89
    ation
    0.88
     inflation
    0.86
     adjustment
    0.86
     rate
    0.85
    rate
    0.84
    Activations Density 0.027%

    No Known Activations