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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6996
    Prev
    Next
    INDEX
    Explanations

    mentions of the action of increasing taxation

    oai_token-act-pair · gpt-3.5-turbo

    references to increasing taxes

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

    No Comments

    Negative Logits
    pedia
    -0.77
     Samoa
    -0.72
    ician
    -0.69
    cas
    -0.67
     snipp
    -0.66
    icity
    -0.65
    inates
    -0.64
     Sco
    -0.64
     vanquished
    -0.62
     Survivor
    -0.61
    POSITIVE LOGITS
     eyebrows
    1.08
    xual
    0.95
     eyebrow
    0.85
    stakes
    0.80
    ulic
    0.78
    rament
    0.75
    INTON
    0.74
     raising
    0.74
    ONEY
    0.73
     incomes
    0.73
    Activations Density 0.022%

    No Known Activations