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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 17037
    Prev
    Next
    INDEX
    Explanations

    words related to the World Trade Center towers

    oai_token-act-pair · gpt-3.5-turbo

    references to the World Trade Center (WTC) Towers and related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERAL
    -0.67
     Sussex
    -0.65
     Herb
    -0.64
     Bapt
    -0.63
    history
    -0.63
    shapeshifter
    -0.63
    WI
    -0.62
     GABA
    -0.62
    Poké
    -0.61
    auc
    -0.61
    POSITIVE LOGITS
     towers
    1.33
     Towers
    1.19
    pread
    0.93
    peed
    0.86
    ysc
    0.85
    inki
    0.84
     buildings
    0.83
     skysc
    0.83
    layer
    0.83
    raper
    0.82
    Activations Density 0.012%

    No Known Activations