© 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. 4-RES-JB
    11. 10397
    Prev
    Next
    INDEX
    Explanations

    keywords related to news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "RELATED" and its variations

    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
    stood
    -0.92
    udi
    -0.74
    arist
    -0.74
    angers
    -0.74
    apers
    -0.70
    atur
    -0.68
    amping
    -0.67
    esthes
    -0.67
    oise
    -0.67
    arest
    -0.66
    POSITIVE LOGITS
     VIDEOS
    1.09
     IMAGES
    1.07
    RELATED
    1.05
     INFORMATION
    0.99
     STOR
    0.94
     ARTICLE
    0.90
     WATCHED
    0.89
     STORY
    0.89
     UPDATE
    0.88
     APPLIC
    0.87
    Activations Density 0.007%

    No Known Activations