© 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. 6-RES-JB
    11. 11958
    Prev
    Next
    INDEX
    Explanations

    dates in the format Month Day, Year and related information

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or mentions of the word "Never."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otle
    -0.74
    eers
    -0.69
     Jindal
    -0.67
    uers
    -0.67
     Burk
    -0.66
    Els
    -0.66
    allery
    -0.66
    retched
    -0.65
    uliffe
    -0.64
     Tags
    -0.63
    POSITIVE LOGITS
    theless
    1.50
    winter
    0.89
    BuyableInstoreAndOnline
    0.83
    mind
    0.82
    entimes
    0.80
     ceases
    0.77
    ices
    0.75
     hesitate
    0.74
    icia
    0.73
     EVER
    0.72
    Activations Density 0.024%

    No Known Activations