© 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. 5570
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency or optimization

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to efficiency 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
    enegger
    -0.80
    warts
    -0.75
    Dream
    -0.75
    acular
    -0.72
     Rober
    -0.70
    yang
    -0.68
    Bone
    -0.68
    wart
    -0.67
    jong
    -0.67
    along
    -0.66
    POSITIVE LOGITS
     efficiency
    1.04
     efficient
    1.01
     allocation
    0.91
    iencies
    0.91
     inefficient
    0.88
     utilization
    0.83
     tract
    0.82
     optimization
    0.81
    idious
    0.78
     minded
    0.78
    Activations Density 0.016%

    No Known Activations