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. 21795
    Prev
    Next
    INDEX
    Explanations

    specific technology-related terms, particularly models and versions of electronics and computing devices

    oai_token-act-pair · gpt-3.5-turbo

    references to various models of electronic devices

    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
    #$#$
    -0.77
    =-=-
    -0.77
    wed
    -0.73
    href
    -0.72
    iets
    -0.68
    meyer
    -0.67
    inating
    -0.67
    âĸ¬
    -0.66
    ynt
    -0.63
    ãĥ´
    -0.63
    POSITIVE LOGITS
     Definitive
    0.84
     Duo
    0.78
    Ħ¢
    0.76
     Dual
    0.75
     Deluxe
    0.74
     Series
    0.70
     Collection
    0.69
    âĦ¢
    0.69
     Portable
    0.67
     Turbo
    0.66
    Activations Density 0.211%

    No Known Activations