© 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. 7-RES-JB
    11. 23521
    Prev
    Next
    INDEX
    Explanations

    terms related to monetary expenses

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary expenses or costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.81
    ullivan
    -0.72
    zinski
    -0.71
    vous
    -0.71
    querque
    -0.70
    fw
    -0.68
    employment
    -0.68
    IJ
    -0.68
    venth
    -0.67
    ramid
    -0.66
    POSITIVE LOGITS
     taxpayers
    1.03
    umed
    1.00
     prohib
    0.96
    umers
    0.91
     savings
    0.89
     incurred
    0.81
    lier
    0.80
     money
    0.78
     overrun
    0.77
     dearly
    0.77
    Activations Density 0.025%

    No Known Activations