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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 10892
    Prev
    Next
    INDEX
    Explanations

    words related to skyscrapers and skylines

    oai_token-act-pair · gpt-3.5-turbo

    references to skyscrapers and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.84
    iotic
    -0.77
    ña
    -0.74
    nia
    -0.71
    nar
    -0.71
    staking
    -0.68
     Recomm
    -0.66
    ãĤ±
    -0.66
    laus
    -0.65
    gas
    -0.65
    POSITIVE LOGITS
     skysc
    1.44
     skyline
    1.34
    raper
    1.31
     towers
    1.02
     tallest
    1.00
     tower
    0.87
     Buildings
    0.83
     Tower
    0.81
     facade
    0.80
    itect
    0.80
    Activations Density 0.017%

    No Known Activations