© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6478
    Prev
    Next
    INDEX
    Explanations

    words related to captions and closing statements in news articles

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to user interface actions, specifically closures or dismissals

    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
    ha
    -0.72
    ãĤ¶
    -0.72
    utical
    -0.69
    maximum
    -0.67
    uca
    -0.66
    Bloom
    -0.65
    factor
    -0.64
     includ
    -0.64
    emis
    -0.64
    duct
    -0.63
    POSITIVE LOGITS
     SHARES
    0.80
     Thumbnails
    0.77
     Close
    0.71
     arming
    0.66
     Annotations
    0.63
    ibrary
    0.62
     Gallery
    0.62
     Copyright
    0.61
     Skip
    0.61
     ABE
    0.59
    Activations Density 0.019%

    No Known Activations