© 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. 7-RES-JB
    11. 23573
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "now"

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases that signify transition or ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÅĤ
    -0.67
    ady
    -0.65
     guiActiveUn
    -0.65
    SourceFile
    -0.63
     Others
    -0.63
    atlantic
    -0.61
    Associated
    -0.60
    atives
    -0.60
    Conservative
    -0.57
     Citiz
    -0.56
    POSITIVE LOGITS
     somew
    1.11
     yeah
    0.97
     please
    0.96
     congr
    0.90
     haha
    0.89
     whenever
    0.83
     alas
    0.81
     yes
    0.81
     however
    0.81
     um
    0.80
    Activations Density 0.429%

    No Known Activations