© 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. 10-RES-JB
    11. 7768
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with "after"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "after" or related phrases suggesting time transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĤ¸
    -0.71
    MENT
    -0.69
    opsis
    -0.69
     guiActiveUn
    -0.69
    cation
    -0.69
    女
    -0.69
    ocry
    -0.68
     endif
    -0.67
     Else
    -0.66
    Else
    -0.66
    POSITIVE LOGITS
     decades
    1.24
     years
    1.19
     months
    1.08
    noon
    1.08
     centuries
    1.05
     witnessing
    1.01
     millennia
    0.97
     exhausting
    0.96
     careful
    0.96
     enduring
    0.94
    Activations Density 0.099%

    No Known Activations