© 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. 3-RES-JB
    11. 529
    Prev
    Next
    INDEX
    Explanations

    phrases related to being a part of something

    oai_token-act-pair · gpt-3.5-turbo

    references to components of a whole or contributions to a larger context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.79
    mare
    -0.70
    asu
    -0.67
    avorite
    -0.66
     ceilings
    -0.65
    bish
    -0.64
     metab
    -0.63
    incinn
    -0.63
    olesc
    -0.63
    usra
    -0.62
    POSITIVE LOGITS
    ials
    0.87
    ially
    0.85
    aking
    0.75
    ners
    0.75
    uary
    0.72
    ioned
    0.72
    meal
    0.71
     adjunct
    0.70
     part
    0.68
    icularly
    0.62
    Activations Density 0.027%

    No Known Activations