© 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. 10-RES-JB
    11. 11414
    Prev
    Next
    INDEX
    Explanations

    sports-related terms, such as league names and events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nodd
    -0.77
     unnecess
    -0.75
     necks
    -0.72
     tack
    -0.71
     spons
    -0.71
    pport
    -0.71
     buyers
    -0.68
     downright
    -0.68
     folk
    -0.68
     slic
    -0.68
    POSITIVE LOGITS
     During
    1.60
     Afterwards
    1.59
     Later
    1.55
     Shortly
    1.50
     Following
    1.46
     Throughout
    1.43
     Eventually
    1.41
     Additionally
    1.40
     Upon
    1.40
     After
    1.35
    Activations Density 0.167%

    No Known Activations