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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18565
    Prev
    Next
    INDEX
    Explanations

    phrases indicating duration or continuous action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating personal experiences or actions taken over time

    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
    ))))
    -0.72
    ildo
    -0.65
    iru
    -0.65
    estial
    -0.59
    annot
    -0.59
    atron
    -0.59
    ãĥ¯ãĥ³
    -0.59
    window
    -0.57
    )))
    -0.56
    ãĤµ
    -0.56
    POSITIVE LOGITS
     lately
    1.57
     since
    1.48
    since
    1.08
     awhile
    0.99
     throughout
    0.97
     intermitt
    0.94
     until
    0.94
     till
    0.93
     countless
    0.91
     hitherto
    0.86
    Activations Density 0.899%

    No Known Activations