© 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. 11-RES-JB
    11. 22488
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find phrases beginning with "After" followed by a time frame

    oai_token-act-pair · gpt-3.5-turbo

    themes and repeated phrases related to duration or periods of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.86
    gi
    -0.80
    terday
    -0.79
    ï¸
    -0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.77
    anooga
    -0.77
    cn
    -0.76
    enth
    -0.73
    deck
    -0.72
    »Ĵ
    -0.71
    POSITIVE LOGITS
     uninterrupted
    1.10
     neglect
    1.05
     inaction
    1.05
     stagnation
    1.04
     relentless
    1.02
     campaigning
    1.00
     experimentation
    0.97
     unrel
    0.96
     litigation
    0.95
     turmoil
    0.94
    Activations Density 0.097%

    No Known Activations