© 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. 3-RES-JB
    11. 23819
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions related to events or actions happening sooner rather than later

    oai_token-act-pair · gpt-3.5-turbo

    phrases predicting imminent events or occurrences

    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
    prison
    -0.79
    Ward
    -0.76
    square
    -0.75
    pel
    -0.72
    ports
    -0.71
    EVA
    -0.70
    mir
    -0.69
    DC
    -0.69
    rug
    -0.68
    bel
    -0.67
    POSITIVE LOGITS
     than
    1.04
     "$:/
    0.90
     Than
    0.88
    aneously
    0.85
     sooner
    0.84
     confir
    0.78
     nodd
    0.78
    than
    0.76
     mosqu
    0.74
     msec
    0.74
    Activations Density 0.012%

    No Known Activations