© 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. 18508
    Prev
    Next
    INDEX
    Explanations

    terms related to societal issues and advancements

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" indicating existence or state

    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
     Archdemon
    -0.69
     Cosponsors
    -0.68
    igent
    -0.65
     Communication
    -0.64
     Recommend
    -0.63
     Supports
    -0.62
     Refer
    -0.61
    ¶
    -0.59
     Monitor
    -0.59
     Concern
    -0.58
    POSITIVE LOGITS
     gone
    1.25
     erased
    1.20
     extinguished
    1.18
     replaced
    1.14
     obliter
    1.13
     fading
    1.13
     disappearing
    1.09
     undone
    1.08
     shattered
    1.07
     evapor
    1.03
    Activations Density 0.317%

    No Known Activations