© 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. 5165
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to sudden events or changes

    oai_token-act-pair · gpt-3.5-turbo

    instances of sudden occurrences or events, particularly those that involve pain or unexpected situations

    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
    fman
    -0.81
     drilled
    -0.72
    models
    -0.70
    adr
    -0.68
    Tex
    -0.67
    gard
    -0.66
    imore
    -0.66
    ippi
    -0.65
     Journals
    -0.64
    halla
    -0.64
    POSITIVE LOGITS
    aneously
    1.34
    aneous
    0.91
    cffffcc
    0.85
     bursts
    0.83
     cardiac
    0.80
     departure
    0.79
     burst
    0.78
     influx
    0.77
     onset
    0.77
     puberty
    0.76
    Activations Density 0.011%

    No Known Activations