© 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. 13360
    Prev
    Next
    INDEX
    Explanations

    action words related to personal financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    words related to taxes and financial participation

    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
    ansky
    -0.76
     extradition
    -0.63
     NAD
    -0.59
     looming
    -0.57
    wig
    -0.56
     backdrop
    -0.55
    adel
    -0.55
     rematch
    -0.55
    oming
    -0.55
     furious
    -0.54
    POSITIVE LOGITS
     previous
    1.11
     prior
    0.99
     previously
    0.95
     earlier
    0.94
     beforehand
    0.90
     preceding
    0.87
     Ago
    0.85
     yesterday
    0.82
     ago
    0.81
     or
    0.79
    Activations Density 0.759%

    No Known Activations