© 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. 10240
    Prev
    Next
    INDEX
    Explanations

    descriptions of buildings, structures, and architectural features

    oai_token-act-pair · gpt-3.5-turbo

    elements related to architecture and historical style

    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
    agonist
    -0.85
     Limit
    -0.82
    dose
    -0.74
     Priority
    -0.70
     CNS
    -0.69
    ursion
    -0.68
    ultane
    -0.68
     Limits
    -0.67
    stakes
    -0.67
    cend
    -0.67
    POSITIVE LOGITS
     decoration
    1.27
     plaster
    1.19
     stained
    1.16
     decorations
    1.15
     ornament
    1.15
     decorative
    1.09
     rust
    1.08
     deteriorated
    1.07
     wallpaper
    1.06
     marble
    1.06
    Activations Density 0.405%

    No Known Activations