© 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. 18600
    Prev
    Next
    INDEX
    Explanations

    buzzwords related to revolutionary technological advancements and changes in various industries

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant changes or transformations in various fields

    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
    erity
    -0.74
    rants
    -0.71
    estones
    -0.71
    estone
    -0.70
    wcsstore
    -0.70
    BLIC
    -0.68
    IDS
    -0.68
    assium
    -0.67
    tan
    -0.66
    maximum
    -0.64
    POSITIVE LOGITS
     warfare
    0.99
     lives
    0.97
     paradigm
    0.96
     perception
    0.94
     landscape
    0.93
     geop
    0.92
     perceptions
    0.90
     fortunes
    0.86
     computing
    0.84
     conceptions
    0.84
    Activations Density 0.233%

    No Known Activations