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. 3-RES-JB
    6. 14191
    Prev
    Next
    INDEX
    Explanations

    words related to "Cerro Paranal" or names containing "Cer" such as "Cecilia" or "Ceramics"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Cerberus" or related keywords

    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
     Buffett
    -0.78
    ãĥĥãĥĪ
    -0.73
     Barkley
    -0.71
    achusetts
    -0.71
    lihood
    -0.70
    sight
    -0.67
    edit
    -0.66
    urst
    -0.65
     Newsweek
    -0.65
    share
    -0.64
    POSITIVE LOGITS
    idian
    1.02
    amic
    0.94
     Cer
    0.93
    isine
    0.91
    oder
    0.88
    ately
    0.86
    osa
    0.84
    acies
    0.84
    vette
    0.81
    oding
    0.80
    Activations Density 0.009%

    No Known Activations