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. 6-RES-JB
    6. 20198
    Prev
    Next
    INDEX
    Explanations

    references to the application "Snapchat"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the social media app "Snapchat."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.84
    vernment
    -0.81
    icist
    -0.74
    uana
    -0.69
     nomine
    -0.67
    ative
    -0.66
    ifference
    -0.64
    ieves
    -0.64
    iosyncr
    -0.63
    mma
    -0.63
    POSITIVE LOGITS
    dragon
    1.15
    shot
    1.03
    shots
    1.00
    laus
    0.92
    chat
    0.90
     snap
    0.89
     snapped
    0.88
    Snap
    0.83
     snapping
    0.81
    snap
    0.80
    Activations Density 0.020%

    No Known Activations