© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 12017
    Prev
    Next
    INDEX
    Explanations

    phrases related to future events or predictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to announcements and predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pired
    -0.66
    istered
    -0.62
    Enter
    -0.59
    RW
    -0.56
    20439
    -0.56
    cffffcc
    -0.55
     supposed
    -0.54
    ĨĴ
    -0.54
    SELECT
    -0.54
    pires
    -0.54
    POSITIVE LOGITS
     someday
    1.11
     tomorrow
    1.05
     hereafter
    0.89
     anytime
    0.85
     soon
    0.74
    morrow
    0.72
     next
    0.71
     sooner
    0.70
     regardless
    0.70
     2019
    0.68
    Activations Density 1.100%

    No Known Activations