© 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. 1-RES-JB
    11. 14320
    Prev
    Next
    INDEX
    Explanations

    terms related to financial turnovers and transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to business metrics and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liam
    -0.84
     behalf
    -0.69
    TERN
    -0.66
    bour
    -0.63
    abol
    -0.63
    este
    -0.62
    encing
    -0.61
    bors
    -0.60
    Brave
    -0.60
     Qual
    -0.60
    POSITIVE LOGITS
     turnover
    1.20
     turnovers
    0.81
     proble
    0.80
     aversion
    0.77
    luster
    0.76
    ftime
    0.74
     retention
    0.72
     Qiao
    0.72
    erning
    0.70
     destro
    0.70
    Activations Density 0.003%

    No Known Activations