© 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. 3-RES-JB
    11. 13517
    Prev
    Next
    INDEX
    Explanations

    various contexts where actions or events are appropriately adjusted or responded to

    oai_token-act-pair · gpt-3.5-turbo

    the word "accordingly" 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
    tein
    -0.78
     Franks
    -0.73
    dan
    -0.71
     Mehran
    -0.71
     Klu
    -0.67
     Roses
    -0.66
    oppable
    -0.65
     Lyme
    -0.64
    ker
    -0.63
    dust
    -0.63
    POSITIVE LOGITS
     accordingly
    0.90
     conduc
    0.89
     enthusi
    0.89
     behavi
    0.86
    wcs
    0.81
    ãĤ¼ãĤ¦ãĤ¹
    0.80
     streng
    0.80
     guiActiveUn
    0.79
     proport
    0.78
    é¾įåĸļ士
    0.78
    Activations Density 0.010%

    No Known Activations