© 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. 11902
    Prev
    Next
    INDEX
    Explanations

    words related to crickets or cricket usage

    oai_token-act-pair · gpt-3.5-turbo

    words that end in specific suffixes related to names and titles

    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
    shire
    -0.64
    èĢħ
    -0.64
     Ji
    -0.62
     Dragonbound
    -0.59
     Illum
    -0.57
     SetTextColor
    -0.57
    atchewan
    -0.56
     discredit
    -0.54
     Downs
    -0.53
     impeachment
    -0.53
    POSITIVE LOGITS
    ¹
    0.88
    ī
    0.86
    »
    0.79
    £
    0.78
    Ĺ
    0.75
    ocol
    0.75
    lass
    0.74
    ĵ
    0.73
    cling
    0.73
    ¯
    0.73
    Activations Density 0.256%

    No Known Activations