© 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. 4-RES-JB
    11. 10345
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential uses or benefits of various technologies or discoveries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to potential uses or applications of technologies or concepts

    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
    ago
    -0.66
    ifa
    -0.66
     Slave
    -0.62
     Scand
    -0.62
    nia
    -0.61
    ÃŃa
    -0.61
    ida
    -0.61
    birth
    -0.61
    vous
    -0.59
    ope
    -0.59
    POSITIVE LOGITS
     applications
    1.14
     Applications
    0.86
     application
    0.83
    afety
    0.83
     relevance
    0.79
    ability
    0.78
    ibilities
    0.77
    Applications
    0.77
    abilities
    0.75
    rehend
    0.75
    Activations Density 0.034%

    No Known Activations