© 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. 3-RES-JB
    11. 23521
    Prev
    Next
    INDEX
    Explanations

    dates and time-related references preceded by the word "ahead"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "ahead of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.80
    anan
    -0.72
    essee
    -0.70
    culosis
    -0.70
     Cosponsors
    -0.69
    ague
    -0.67
    anos
    -0.67
    ulas
    -0.65
    anut
    -0.64
    cular
    -0.63
    POSITIVE LOGITS
     ours
    0.85
     course
    0.83
     8000
    0.77
     mine
    0.75
     1200
    0.70
     7000
    0.69
     theirs
    0.68
     hers
    0.67
     1600
    0.67
     yours
    0.65
    Activations Density 0.115%

    No Known Activations