© 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. 4069
    Prev
    Next
    INDEX
    Explanations

    mentions of interior design features

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "interior" in various contexts

    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
    tle
    -0.78
    bilt
    -0.78
    tailed
    -0.78
    nir
    -0.77
    astically
    -0.71
    frog
    -0.71
    nown
    -0.69
    isSpecialOrderable
    -0.69
    join
    -0.68
    yip
    -0.67
    POSITIVE LOGITS
     decoration
    1.05
     ministry
    1.01
     decor
    0.96
     Designer
    0.92
     designer
    0.89
     decorations
    0.82
     designers
    0.82
     design
    0.81
    most
    0.80
     renovation
    0.77
    Activations Density 0.048%

    No Known Activations