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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 4396
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific plaza locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or places, particularly plazas

    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
    ERAL
    -0.82
    ebook
    -0.76
    went
    -0.75
    nesses
    -0.72
    gets
    -0.70
    loss
    -0.67
    liest
    -0.66
    SOURCE
    -0.65
    wcsstore
    -0.63
    etimes
    -0.62
    POSITIVE LOGITS
     Plaza
    1.40
     plaza
    1.04
     Hotel
    0.92
     Blvd
    0.86
     Square
    0.86
     Coliseum
    0.81
    itect
    0.81
    ards
    0.81
     Boulevard
    0.79
    adium
    0.78
    Activations Density 0.008%

    No Known Activations