Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 21406
    Prev
    Next
    INDEX
    Explanations

    terms related to extended time periods or events

    oai_token-act-pair · gpt-3.5-turbo

    the term "prolonged" and related concepts indicating extended duration or persistence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -1.01
    iquette
    -0.84
    busters
    -0.83
    girls
    -0.82
    ologies
    -0.79
     Cosponsors
    -0.78
    tical
    -0.78
    girl
    -0.76
    posted
    -0.75
    illard
    -0.75
    POSITIVE LOGITS
     periods
    1.03
     prolong
    0.94
     postp
    0.83
     lasting
    0.83
     delays
    0.83
     bouts
    0.81
    ignt
    0.80
     miscarriage
    0.80
     prolonged
    0.78
     ende
    0.77
    Activations Density 0.014%

    No Known Activations