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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 2041
    Prev
    Next
    INDEX
    Explanations

    Las Vegas-related content

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "Las Vegas."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boards
    -0.77
     facult
    -0.72
    alog
    -0.72
    alys
    -0.71
    arist
    -0.71
    Ü
    -0.70
    ä
    -0.69
    work
    -0.69
    ħ
    -0.69
    framework
    -0.68
    POSITIVE LOGITS
     Vegas
    1.08
     Lumpur
    1.02
     Boulevard
    0.97
     Strip
    0.92
     Blvd
    0.90
     Sands
    0.89
     Metropolitan
    0.83
     casinos
    0.83
     Casino
    0.81
     Reno
    0.80
    Activations Density 0.008%

    No Known Activations