© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 17881
    Prev
    Next
    INDEX
    Explanations

    terms related to optimization or words related to improving efficiency

    oai_token-act-pair · gpt-3.5-turbo

    terms related to optimization processes and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.82
    mad
    -0.81
    ere
    -0.79
    lust
    -0.75
    rough
    -0.74
    bearing
    -0.72
    ken
    -0.72
    chal
    -0.70
    areth
    -0.70
    lis
    -0.70
    POSITIVE LOGITS
     optimization
    1.32
     optimize
    1.17
     optimizing
    1.06
     optimizations
    1.05
     optim
    1.03
     Optim
    0.99
     optimized
    0.94
     allocation
    0.87
     partName
    0.80
     efficiency
    0.78
    Activations Density 0.019%

    No Known Activations