© 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. 10013
    Prev
    Next
    INDEX
    Explanations

    phrases related to household maintenance and repairs

    oai_token-act-pair · gpt-3.5-turbo

    references to household items and their arrangement

    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
    -0.83
    onomous
    -0.82
    href
    -0.78
    owship
    -0.75
    rica
    -0.74
    GGGG
    -0.73
    utan
    -0.73
     Saga
    -0.71
    Hero
    -0.69
    aido
    -0.69
    POSITIVE LOGITS
     ceilings
    1.84
     windows
    1.71
     ceiling
    1.70
     floors
    1.59
     curtains
    1.57
     roofs
    1.54
     doors
    1.54
     cabinets
    1.54
     walls
    1.53
     wallpaper
    1.51
    Activations Density 0.398%

    No Known Activations