© 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. 11-RES-JB
    11. 22483
    Prev
    Next
    INDEX
    Explanations

    decorative descriptions related to ornate designs and artifacts

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of intricate designs and decorations in artifacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lease
    -0.91
     Startup
    -0.81
     Shutdown
    -0.77
     Supervisor
    -0.77
     commute
    -0.76
    osphere
    -0.76
     Subway
    -0.76
    odcast
    -0.75
     Collider
    -0.75
    Zone
    -0.75
    POSITIVE LOGITS
     bronze
    1.44
     ornament
    1.37
     laure
    1.34
     ivory
    1.29
     brass
    1.28
     jewels
    1.27
     embro
    1.26
     spears
    1.26
     lantern
    1.24
     inscribed
    1.23
    Activations Density 0.209%

    No Known Activations