© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16550
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific timeframes or deadlines

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time-sensitive events or deadlines

    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
    catentry
    -0.86
    ryu
    -0.78
    obyl
    -0.77
    oglu
    -0.77
    ioxid
    -0.76
    phas
    -0.75
    uterte
    -0.75
    assad
    -0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
    igion
    -0.74
    POSITIVE LOGITS
     onlook
    0.89
     passers
    0.83
     Eater
    0.82
     locals
    0.82
     Nope
    0.81
     TMZ
    0.81
     Deadline
    0.78
     folks
    0.78
     FOX
    0.77
     CBS
    0.76
    Activations Density 0.748%

    No Known Activations