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. 7861
    Prev
    Next
    INDEX
    Explanations

    phrases related to step-by-step instructions and procedures

    oai_token-act-pair · gpt-3.5-turbo

    expressions of necessity or requirement

    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
     Malays
    -0.54
     Malaysia
    -0.48
     Pigs
    -0.47
     Lumpur
    -0.46
     Lion
    -0.44
     Kuala
    -0.43
     Mandatory
    -0.43
     Recre
    -0.43
     Lit
    -0.42
     Higher
    -0.42
    POSITIVE LOGITS
    pmwiki
    0.67
    âĵĺ
    0.62
     nonetheless
    0.59
    etheless
    0.55
     nevertheless
    0.53
    bably
    0.50
    ãĤ¦ãĤ¹
    0.49
    ãĥĩãĤ£
    0.47
    gui
    0.47
    ãĥĦ
    0.47
    Activations Density 2.050%

    No Known Activations