© 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. 1-RES-JB
    11. 3379
    Prev
    Next
    INDEX
    Explanations

    mentions or references to something being highlighted, showcased, or presented prominently

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "featured."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thur
    -0.96
    sis
    -0.84
    cel
    -0.76
    apa
    -0.76
    batch
    -0.73
    wake
    -0.72
    uters
    -0.72
    neg
    -0.71
    separ
    -0.71
    nesia
    -0.70
    POSITIVE LOGITS
     prominently
    1.40
     featured
    1.05
    Featured
    1.02
     Featured
    0.87
     Include
    0.84
     Features
    0.83
     features
    0.83
    Feature
    0.80
    features
    0.79
     Topics
    0.74
    Activations Density 0.010%

    No Known Activations