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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 17042
    Prev
    Next
    INDEX
    Explanations

    references to businesses or commercial entities

    oai_token-act-pair · gpt-3.5-turbo

    references to businesses and commercial activity

    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
     Symptoms
    -0.64
     Verge
    -0.63
    anche
    -0.62
     Surgery
    -0.61
     Janeiro
    -0.61
     Gren
    -0.59
     Huss
    -0.59
    sson
    -0.58
    rawdownloadcloneembedreportprint
    -0.58
    alys
    -0.58
    POSITIVE LOGITS
    folk
    1.02
     owners
    1.00
     establishments
    0.97
     owner
    0.94
     enterprises
    0.89
    INESS
    0.85
    owner
    0.84
    owners
    0.83
     businesses
    0.83
    mens
    0.81
    Activations Density 0.037%

    No Known Activations