© 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. 8-RES-JB
    11. 7895
    Prev
    Next
    INDEX
    Explanations

    the phrase "as long as"

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the condition of duration or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.64
    psey
    -0.62
    åĤ
    -0.62
    IRO
    -0.61
     guiActiveUn
    -0.60
    æĺ
    -0.60
    chat
    -0.58
    COMPLE
    -0.58
    ãĥ´ãĤ¡
    -0.58
    ascus
    -0.58
    POSITIVE LOGITS
     ago
    1.12
    itud
    0.99
    itude
    0.94
     overdue
    0.91
    term
    0.84
     stretches
    0.74
    itudinal
    0.74
    terms
    0.74
    bows
    0.73
    lasting
    0.72
    Activations Density 0.027%

    No Known Activations