© 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. 10575
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Gener" accompanied by varying degrees of a positive sentiment or association

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Gener" or related generational themes

    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
    ĺħ
    -0.77
    yer
    -0.70
    mare
    -0.69
    eneg
    -0.68
    clair
    -0.64
     Madison
    -0.63
    wal
    -0.62
    ware
    -0.62
    rock
    -0.61
    EEP
    -0.60
    POSITIVE LOGITS
    ational
    1.41
    osity
    1.41
    ators
    1.29
    ative
    1.23
    icity
    1.17
    ously
    1.14
    ations
    1.14
    ically
    1.10
    andum
    1.10
    ics
    1.10
    Activations Density 0.035%

    No Known Activations