© 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. 9-RES-JB
    11. 15871
    Prev
    Next
    INDEX
    Explanations

    statistical and mathematical terms related to measurements and calculations

    oai_token-act-pair · gpt-3.5-turbo

    metrics and measurements related to life expectancy and statistical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aroo
    -0.73
     affairs
    -0.71
     acad
    -0.70
    natureconservancy
    -0.68
     themed
    -0.67
     hij
    -0.66
     Archives
    -0.66
     sandbox
    -0.65
     recons
    -0.64
    ublic
    -0.62
    POSITIVE LOGITS
     ratio
    1.37
     coefficient
    1.35
     Ratio
    1.32
     percentage
    1.32
     metric
    1.25
     percentile
    1.24
     coefficients
    1.22
     Percentage
    1.21
     ratios
    1.20
     measurement
    1.20
    Activations Density 0.572%

    No Known Activations