© 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. 1871
    Prev
    Next
    INDEX
    Explanations

    phrases related to a small amount or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a small degree of something

    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
    ulner
    -0.77
    ayn
    -0.74
    SEA
    -0.68
     DG
    -0.67
    STD
    -0.66
     Wast
    -0.65
     Ancest
    -0.65
     Daly
    -0.63
     Cosponsors
    -0.63
     Warehouse
    -0.61
    POSITIVE LOGITS
    pload
    0.75
     whisk
    0.71
     lemon
    0.65
    ¬¼
    0.64
     peeled
    0.63
     forgiven
    0.62
     peel
    0.61
     luck
    0.61
     trickle
    0.61
     scratch
    0.61
    Activations Density 0.305%

    No Known Activations