© 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. 4-RES-JB
    11. 5109
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations or buildings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and references to geographical locations, particularly plazas

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

    No Comments

    Negative Logits
    liest
    -0.85
    ERAL
    -0.76
    gets
    -0.73
    nesses
    -0.71
    lessly
    -0.70
    matter
    -0.69
    wcsstore
    -0.68
    ebook
    -0.67
    went
    -0.65
    manship
    -0.64
    POSITIVE LOGITS
     Plaza
    1.27
     Hotel
    1.01
     plaza
    0.85
     Blvd
    0.82
     Hilton
    0.81
     Boulevard
    0.79
     Square
    0.77
     Avenue
    0.76
     Coliseum
    0.75
     Corridor
    0.74
    Activations Density 0.011%

    No Known Activations