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. 1-RES-JB
    6. 17888
    Prev
    Next
    INDEX
    Explanations

    locations or venues, particularly with the word "Plaza" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or plazas

    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
    went
    -0.77
    ebook
    -0.75
    gets
    -0.75
    wcsstore
    -0.71
    ERAL
    -0.69
    nesses
    -0.69
    liest
    -0.68
    loss
    -0.67
    young
    -0.65
    dit
    -0.64
    POSITIVE LOGITS
     Plaza
    1.45
     plaza
    1.15
     Hotel
    0.93
     Square
    0.84
     Coliseum
    0.82
    emonium
    0.82
     Blvd
    0.81
    itect
    0.81
     Corridor
    0.79
     kios
    0.78
    Activations Density 0.008%

    No Known Activations