© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10140
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial affordability

    oai_token-act-pair · gpt-3.5-turbo

    references to financial capability or the inability to cover expenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Straw
    -0.77
     Soccer
    -0.62
     Jihad
    -0.62
     Kills
    -0.61
    PM
    -0.61
     Negative
    -0.61
    NC
    -0.59
     Translation
    -0.59
    nation
    -0.59
    TC
    -0.59
    POSITIVE LOGITS
     afford
    3.74
     afforded
    1.63
    ordable
    1.17
     cheaply
    1.14
     sustain
    1.10
     affordability
    1.06
     furnish
    1.05
     affordable
    1.04
     tolerate
    1.02
    Aff
    1.01
    Activations Density 0.018%

    No Known Activations