© 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. 4363
    Prev
    Next
    INDEX
    Explanations

    Phrases related to current news events and announcements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "today"

    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
     Conquer
    -0.81
     Trouble
    -0.76
    emaker
    -0.65
    aughed
    -0.65
     Viz
    -0.64
    chief
    -0.62
    chest
    -0.62
    ories
    -0.62
    anon
    -0.62
    lasses
    -0.62
    POSITIVE LOGITS
     afternoon
    1.24
     morning
    1.13
     evening
    1.11
     mornings
    0.79
     unveiling
    0.75
    morning
    0.75
     announcing
    0.74
    MAR
    0.73
     night
    0.71
    ILA
    0.69
    Activations Density 0.068%

    No Known Activations