© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 3024
    Prev
    Next
    INDEX
    Explanations

    phrases related to time intervals or occurrences, typically phrases indicating sporadic events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omy
    -0.70
    minecraft
    -0.66
     Merrill
    -0.65
    aila
    -0.64
     Ludwig
    -0.64
    ipel
    -0.63
    xual
    -0.62
    utenberg
    -0.59
    uge
    -0.58
    SourceFile
    -0.57
    POSITIVE LOGITS
     Tomorrow
    0.86
     Forever
    0.84
     tomorrow
    0.79
     hereafter
    0.78
     2024
    0.77
     peril
    0.75
     2050
    0.74
     2030
    0.69
     eternity
    0.69
     forever
    0.68
    Activations Density 0.101%

    No Known Activations