© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 8111
    Prev
    Next
    INDEX
    Explanations

    references to showcasing and featuring items or collections

    oai_token-act-pair · gpt-3.5-turbo

    references to events and items related to cultural exhibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesty
    -0.73
    efficiency
    -0.70
     fearing
    -0.69
    endment
    -0.68
    idation
    -0.68
    icum
    -0.67
    Nusra
    -0.65
    alion
    -0.65
    PsyNetMessage
    -0.65
    Setup
    -0.65
    POSITIVE LOGITS
     classics
    1.25
     artists
    1.06
     originals
    1.05
     iconic
    1.04
     genres
    1.03
     eclectic
    0.99
     favorites
    0.94
     classic
    0.93
     contemporary
    0.92
     vintage
    0.90
    Activations Density 0.638%

    No Known Activations