© 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. 0-RES-JB
    11. 1334
    Prev
    Next
    INDEX
    Explanations

    numerical values related to calculations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "calculated" in various contexts related to numerical or statistical assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    archives
    -0.66
    ishes
    -0.65
    Later
    -0.63
    stay
    -0.63
    vine
    -0.62
    oa
    -0.61
    ender
    -0.61
    forts
    -0.60
    Topics
    -0.59
    Rust
    -0.59
    POSITIVE LOGITS
     calculated
    3.57
     calculating
    1.94
     computed
    1.93
     calculate
    1.92
     calculates
    1.91
     calculation
    1.85
     measured
    1.73
     Calcul
    1.72
     calculations
    1.61
     plotted
    1.55
    Activations Density 0.009%

    No Known Activations