© 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. 8-RES-JB
    11. 8033
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to selling, buying, or transactions

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to sales or transactions

    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
    arta
    -0.68
    osal
    -0.63
    INGTON
    -0.62
     purs
    -0.60
    gart
    -0.60
    iah
    -0.60
     parting
    -0.59
    itia
    -0.59
    verting
    -0.57
    ft
    -0.56
    POSITIVE LOGITS
     prominently
    0.87
     smoothly
    0.83
     nicely
    0.79
     seamlessly
    0.75
     differently
    0.74
     favorably
    0.72
     exactly
    0.71
     unbeliev
    0.71
     surprisingly
    0.71
     itself
    0.70
    Activations Density 0.273%

    No Known Activations