© 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. 18373
    Prev
    Next
    INDEX
    Explanations

    instances of items being categorized into different types or groups

    oai_token-act-pair · gpt-3.5-turbo

    structures and classifications involving numbers and categories

    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
    vez
    -0.74
    amaru
    -0.72
    brance
    -0.72
    hire
    -0.69
    reb
    -0.67
    potion
    -0.67
    hers
    -0.66
    encer
    -0.64
    $$
    -0.64
    ifice
    -0.64
    POSITIVE LOGITS
     kinds
    1.25
     types
    1.24
     distinct
    1.18
     phases
    1.18
     tiers
    1.06
     main
    1.06
     categories
    1.04
     stages
    1.02
     different
    1.01
     ways
    1.00
    Activations Density 0.157%

    No Known Activations