© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9212
    Prev
    Next
    INDEX
    Explanations

    social media-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to social media engagement, particularly shares

    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
    istically
    -0.85
    tis
    -0.80
    omen
    -0.74
    olog
    -0.73
    eal
    -0.70
    ras
    -0.66
     Mamm
    -0.66
     Daly
    -0.66
    stress
    -0.66
     Jub
    -0.66
    POSITIVE LOGITS
     SHARES
    1.22
     Tradable
    0.79
    poons
    0.74
     Shares
    0.73
     VIDEOS
    0.70
     Share
    0.70
    NECT
    0.69
    nesday
    0.69
    ABLE
    0.69
    OTUS
    0.69
    Activations Density 0.008%

    No Known Activations