© 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. 0-RES-JB
    11. 1530
    Prev
    Next
    INDEX
    Explanations

    instances where an action is expected or required to persist over time

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "continue."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oret
    -0.59
    ophy
    -0.58
    oid
    -0.58
     Born
    -0.58
    ising
    -0.57
    pes
    -0.57
    bies
    -0.57
    ody
    -0.55
    unes
    -0.55
    ius
    -0.55
    POSITIVE LOGITS
     continue
    3.31
    continue
    2.65
     continues
    2.17
     continued
    2.03
     remain
    1.93
     continuing
    1.88
     Continue
    1.84
     CONTIN
    1.75
    Continue
    1.74
     proceed
    1.67
    Activations Density 0.023%

    No Known Activations