© 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. 1-RES-JB
    11. 3835
    Prev
    Next
    INDEX
    Explanations

    phrases related to summarizing information or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "recap" in various contexts, particularly in summaries of events or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trafford
    -0.72
     Wee
    -0.66
     Mustang
    -0.64
    âĢ¢âĢ¢
    -0.62
    erness
    -0.61
     marriage
    -0.61
    mouth
    -0.59
     wounding
    -0.58
     cigarettes
    -0.58
    young
    -0.57
    POSITIVE LOGITS
     recap
    1.53
     Recap
    1.12
    ital
    1.01
    odcast
    0.93
    ilitation
    0.90
    enda
    0.85
    imation
    0.84
    itect
    0.79
    itations
    0.78
    apon
    0.77
    Activations Density 0.006%

    No Known Activations