© 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. 9-RES-JB
    11. 9858
    Prev
    Next
    INDEX
    Explanations

    it is looking for instances related to rapid changes or growth

    oai_token-act-pair · gpt-3.5-turbo

    markers indicating a rapid state or change, particularly in growth or development contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Parables
    -0.79
    warts
    -0.78
    olphins
    -0.76
    agra
    -0.73
    bah
    -0.72
     Borders
    -0.71
    dds
    -0.67
    #$#$
    -0.65
    fortable
    -0.65
     beware
    -0.63
    POSITIVE LOGITS
     paced
    1.04
    ity
    1.01
     succession
    1.01
    aneously
    0.95
     ascent
    0.95
     onset
    0.94
     prototyp
    0.92
     influx
    0.90
     deterioration
    0.90
    increasing
    0.87
    Activations Density 0.050%

    No Known Activations