© 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. 1-RES-JB
    11. 3511
    Prev
    Next
    INDEX
    Explanations

    dates and periods of time, specifically referencing events that happened a certain number of years ago

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "ago," particularly in various contexts indicating time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uniqueness
    -0.86
     simultaneous
    -0.76
     determination
    -0.72
     similarity
    -0.70
     similarities
    -0.69
     mobility
    -0.68
     suspic
    -0.68
     emphasis
    -0.66
     intensity
    -0.66
     comfort
    -0.66
    POSITIVE LOGITS
    ago
    1.34
    vernment
    1.29
    allo
    0.97
    edia
    0.96
    opa
    0.94
    zzi
    0.88
    onte
    0.87
    etta
    0.85
    onz
    0.84
    wright
    0.81
    Activations Density 0.003%

    No Known Activations