© 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. 5447
    Prev
    Next
    INDEX
    Explanations

    words related to quick actions or solutions

    oai_token-act-pair · gpt-3.5-turbo

    the word "quick" in various contexts

    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
    âĹ¼
    -0.80
    Ãį
    -0.74
    iosyncr
    -0.69
    obyl
    -0.67
    INA
    -0.66
    ichick
    -0.66
    ruption
    -0.66
     Seah
    -0.66
     Hof
    -0.65
     Katz
    -0.64
    POSITIVE LOGITS
    aneously
    1.07
    itude
    1.06
    ened
    1.05
     succession
    1.03
     turnaround
    1.02
    ening
    1.01
     enough
    0.90
     glance
    0.89
    lime
    0.88
    eners
    0.85
    Activations Density 0.011%

    No Known Activations