© 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. 3-RES-JB
    11. 13371
    Prev
    Next
    INDEX
    Explanations

    words related to optimization, such as "optimize" and "optimization."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to optimization processes 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
    76561
    -0.86
    soever
    -0.82
    lain
    -0.76
    rough
    -0.74
    FACE
    -0.74
    ere
    -0.74
    avid
    -0.73
    ĸļ
    -0.73
    emonic
    -0.72
    maid
    -0.71
    POSITIVE LOGITS
     optimization
    1.22
     optimize
    1.09
     optim
    1.01
     optimizations
    1.00
     Optim
    0.99
     optimizing
    0.94
     optimized
    0.83
    bably
    0.79
     Suite
    0.76
     allocation
    0.75
    Activations Density 0.013%

    No Known Activations