Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1656
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude, appreciation, and support

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toggle
    -0.75
     guiActiveUn
    -0.62
     Worse
    -0.61
    umably
    -0.60
    edit
    -0.60
    udo
    -0.57
     filler
    -0.57
     Panic
    -0.55
     dummy
    -0.55
    imp
    -0.54
    POSITIVE LOGITS
     courageous
    0.83
     wonderful
    0.82
     sacrific
    0.79
     compassionate
    0.77
     multicultural
    0.77
     excellence
    0.76
    cellence
    0.75
     responsibly
    0.74
     vibrant
    0.74
     magnificent
    0.74
    Activations Density 2.020%

    No Known Activations