© 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. 5373
    Prev
    Next
    INDEX
    Explanations

    terms related to optimization and best outcomes

    oai_token-act-pair · gpt-3.5-turbo

    terms relating to optimization and optimal solutions

    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
    ker
    -0.98
    bara
    -0.87
    mad
    -0.80
    kers
    -0.79
    otten
    -0.77
    hips
    -0.75
    erie
    -0.74
    planes
    -0.71
    ings
    -0.71
    chu
    -0.71
    POSITIVE LOGITS
     equilibrium
    0.95
     optimization
    0.94
     efficiency
    0.93
     outcomes
    0.92
     optimum
    0.91
     ratios
    0.87
     optimal
    0.86
    imum
    0.85
     probability
    0.84
    ritional
    0.83
    Activations Density 0.017%

    No Known Activations