© 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. 2300
    Prev
    Next
    INDEX
    Explanations

    headlines or snippets related to current events or updates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "current."

    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
    romeda
    -0.84
    jah
    -0.83
    amy
    -0.80
    anguage
    -0.79
    aths
    -0.77
    essen
    -0.72
    eneg
    -0.72
    alty
    -0.70
    ppings
    -0.69
    iced
    -0.68
    POSITIVE LOGITS
     incarnation
    1.01
     whereabouts
    0.94
     iteration
    0.88
     predicament
    0.84
     occupant
    0.78
     trends
    0.71
     crop
    0.70
     circumstances
    0.69
    ties
    0.69
     affairs
    0.67
    Activations Density 0.028%

    No Known Activations