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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 1521
    Prev
    Next
    INDEX
    Explanations

    references to the city of Las Vegas

    oai_token-act-pair · gpt-3.5-turbo

    references to Las Vegas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ç
    -0.74
     notified
    -0.68
     labou
    -0.68
     detach
    -0.66
     retard
    -0.65
    Åį
    -0.65
     arch
    -0.65
     dispos
    -0.64
     subjected
    -0.64
    Äģ
    -0.64
    POSITIVE LOGITS
     Vegas
    4.09
     Las
    1.77
    Las
    1.73
     Nevada
    1.59
     Reno
    1.49
     MGM
    1.40
     casinos
    1.37
     Paddock
    1.29
     Casino
    1.25
     Tucson
    1.24
    Activations Density 0.008%

    No Known Activations