© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17559
    Prev
    Next
    INDEX
    Explanations

    the word "skyscraper" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to skyscrapers and urban architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ña
    -0.72
    nar
    -0.68
    iotic
    -0.66
     Recomm
    -0.65
    ELY
    -0.64
    cue
    -0.64
    ktop
    -0.63
    OST
    -0.63
     Immun
    -0.63
    ãĤ±
    -0.62
    POSITIVE LOGITS
     skysc
    1.46
    raper
    1.41
     skyline
    1.07
     towers
    0.97
     condos
    0.92
    itect
    0.92
     buildings
    0.84
     tower
    0.82
     tallest
    0.82
     Towers
    0.82
    Activations Density 0.023%

    No Known Activations