© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    references to financial compensation or payment in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to compensation and reparations

    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
    stead
    -0.81
    jah
    -0.75
    sonian
    -0.74
    agram
    -0.73
    abad
    -0.70
    bum
    -0.70
    stones
    -0.67
     Willow
    -0.66
    forth
    -0.66
    ova
    -0.64
    POSITIVE LOGITS
     compensation
    0.98
     compensate
    0.96
     compensated
    0.91
     compens
    0.90
     expense
    0.87
     claimants
    0.85
    giving
    0.84
     reimburse
    0.83
    SG
    0.82
    ursed
    0.81
    Activations Density 0.031%

    No Known Activations