Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7956
    Prev
    Next
    INDEX
    Explanations

    words related to metrics and measurements

    oai_token-act-pair · gpt-3.5-turbo

    significant factors affecting financial measurements and economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prank
    -0.72
     Canaver
    -0.68
    Brave
    -0.66
    arnaev
    -0.65
    oppers
    -0.64
    mop
    -0.64
    venth
    -0.62
    odore
    -0.62
    çīĪ
    -0.62
    wings
    -0.62
    POSITIVE LOGITS
     measurement
    1.66
     measure
    1.52
     indicator
    1.52
     metrics
    1.50
     metric
    1.46
     indicators
    1.44
     measuring
    1.42
     correlate
    1.41
     measured
    1.40
     quant
    1.39
    Activations Density 0.434%

    No Known Activations