© 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. 1-RES-JB
    11. 7237
    Prev
    Next
    INDEX
    Explanations

    instances where something remains or is indicated to remain in a particular state or condition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "remain" indicating persistence or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idden
    -0.65
    ifice
    -0.65
    assi
    -0.63
     externalToEVAOnly
    -0.62
    ranch
    -0.61
     Tribune
    -0.61
    urated
    -0.61
     opener
    -0.60
    tained
    -0.60
    ilar
    -0.60
    POSITIVE LOGITS
     unchanged
    0.97
     unanswered
    0.90
     undecided
    0.90
    rences
    0.86
     unsolved
    0.79
    emate
    0.78
    Hung
    0.73
    ATURES
    0.73
     intact
    0.72
     unaffected
    0.72
    Activations Density 0.016%

    No Known Activations