© 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. 10-RES-JB
    11. 8235
    Prev
    Next
    INDEX
    Explanations

    terms related to social media and internet culture

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe the internet and social media as influential sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Achieve
    -0.78
    IOR
    -0.74
    PLA
    -0.72
    onds
    -0.70
    udeau
    -0.69
     Highlights
    -0.69
    chev
    -0.68
    ailed
    -0.67
    rouse
    -0.67
    Result
    -0.66
    POSITIVE LOGITS
     littered
    1.16
     rife
    1.16
     notoriously
    1.02
     overflowing
    1.01
     buzzing
    1.01
     inund
    1.00
     flooded
    0.99
     biased
    0.99
     staffed
    0.96
     rigged
    0.93
    Activations Density 0.282%

    No Known Activations