© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7610
    Prev
    Next
    INDEX
    Explanations

    references to buildings being repurposed or renovated

    oai_token-act-pair · gpt-3.5-turbo

    references to redevelopment and repurposing of former buildings or sites

    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
    rared
    -0.80
    flix
    -0.77
    ggle
    -0.74
    intent
    -0.74
    nesota
    -0.73
    allah
    -0.73
    nesday
    -0.73
    sense
    -0.69
    rils
    -0.67
    ensitivity
    -0.67
    POSITIVE LOGITS
     warehouses
    1.33
     buildings
    1.30
     demolished
    1.28
     abandoned
    1.27
     crumbling
    1.23
     dere
    1.19
     wrecked
    1.19
     decaying
    1.19
     defunct
    1.16
     obsolete
    1.15
    Activations Density 0.310%

    No Known Activations