© 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. 7-RES-JB
    11. 12436
    Prev
    Next
    INDEX
    Explanations

    notifications or notifications about events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to notification and informing others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.80
    quer
    -0.71
     imagination
    -0.65
     rug
    -0.65
     rhet
    -0.64
    ucket
    -0.62
     goggles
    -0.61
    shell
    -0.61
    ument
    -0.60
     mustache
    -0.59
    POSITIVE LOGITS
     impending
    1.27
     whereabouts
    0.99
     imminent
    0.86
     dangers
    0.85
     arrival
    0.84
    coming
    0.82
     incoming
    0.78
     receipt
    0.76
     intention
    0.75
     danger
    0.74
    Activations Density 0.246%

    No Known Activations