© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 5098
    Prev
    Next
    INDEX
    Explanations

    the word "spent."

    oai_token-act-pair · gpt-3.5-turbo

    words related to expenditure or spending

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

    No Comments

    Negative Logits
    jar
    -0.83
    vision
    -0.61
    paio
    -0.61
    itans
    -0.57
    amber
    -0.57
     crawl
    -0.56
    tra
    -0.56
    aughtered
    -0.56
    Russell
    -0.56
     Statue
    -0.56
    POSITIVE LOGITS
    staking
    0.84
     lav
    0.84
    itures
    0.82
    iture
    0.81
     âĤ¬
    0.79
     Donation
    0.78
    natureconservancy
    0.77
     £
    0.74
     IPM
    0.72
    ãĤ£
    0.70
    Activations Density 0.023%

    No Known Activations