© 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. 11189
    Prev
    Next
    INDEX
    Explanations

    mentions of current events or actions happening now

    oai_token-act-pair · gpt-3.5-turbo

    the word "now" indicating present actions or statuses

    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
    obos
    -0.76
    insula
    -0.69
    ogi
    -0.69
    sym
    -0.69
    ashes
    -0.68
    zag
    -0.66
    ambo
    -0.66
    Strength
    -0.64
    monds
    -0.63
    ppings
    -0.63
    POSITIVE LOGITS
    adays
    1.36
     defunct
    1.01
     underway
    0.93
    here
    0.92
     obsolete
    0.84
     officially
    0.80
     slated
    0.79
     extinct
    0.79
     nearing
    0.75
     extant
    0.75
    Activations Density 0.062%

    No Known Activations