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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14950
    Prev
    Next
    INDEX
    Explanations

    the word "earliest" occurring in context

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "earliest" in relation to events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.91
    par
    -0.87
    mbuds
    -0.80
    do
    -0.75
    pl
    -0.72
    went
    -0.72
    mund
    -0.69
    chrom
    -0.69
    pers
    -0.68
    aths
    -0.68
    POSITIVE LOGITS
     responders
    0.93
     incarnation
    0.91
     adop
    0.90
     earliest
    0.85
     arri
    0.81
     stages
    0.76
     iteration
    0.76
     ancestor
    0.73
     beginnings
    0.72
    liest
    0.72
    Activations Density 0.003%

    No Known Activations