Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10852
    Prev
    Next
    INDEX
    Explanations

    information related to famous buildings and architectural structures

    oai_token-act-pair · gpt-3.5-turbo

    references to significant architectural structures and their characteristics

    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
     saliva
    -0.90
     abstinence
    -0.89
    dit
    -0.79
     volunt
    -0.76
     tribes
    -0.75
    estern
    -0.75
     clipboard
    -0.73
    hunt
    -0.73
    wcsstore
    -0.72
     Grimes
    -0.72
    POSITIVE LOGITS
     skysc
    1.71
     tower
    1.64
     tallest
    1.64
     towers
    1.58
     WTC
    1.40
     Tower
    1.40
     Towers
    1.36
     taller
    1.28
     buildings
    1.23
    tower
    1.21
    Activations Density 0.258%

    No Known Activations