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. 2265
    Prev
    Next
    INDEX
    Explanations

    the word "crazy" with high activations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "crazy."

    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
    Reviewed
    -0.93
    fman
    -0.85
    tein
    -0.81
    agle
    -0.80
    arers
    -0.80
    ãĥĺãĥ©
    -0.79
    ribut
    -0.78
    lain
    -0.77
    apers
    -0.76
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.75
    POSITIVE LOGITS
     crazy
    0.77
     nuts
    0.76
     shit
    0.73
    spawn
    0.72
     beasts
    0.69
    astically
    0.66
     chic
    0.65
     antics
    0.65
    ishly
    0.65
     fringe
    0.63
    Activations Density 0.023%

    No Known Activations