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. 8-RES-JB
    6. 6589
    Prev
    Next
    INDEX
    Explanations

    social media related content, specifically focusing on activities and interactions on platforms such as Facebook and Twitter

    oai_token-act-pair · gpt-3.5-turbo

    activities related to social media interactions and online behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conclud
    -0.67
    ONSORED
    -0.60
    itutional
    -0.59
    士
    -0.59
     jurisd
    -0.59
    istani
    -0.58
    rition
    -0.57
    ELY
    -0.56
    PDATE
    -0.55
     Vaugh
    -0.55
    POSITIVE LOGITS
     emoji
    0.74
     caption
    0.71
     nude
    0.70
     vagina
    0.69
     GIF
    0.68
     boobs
    0.68
     fake
    0.68
     poop
    0.66
     selfies
    0.64
     cartoon
    0.63
    Activations Density 1.098%

    No Known Activations