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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 22796
    Prev
    Next
    INDEX
    Explanations

    phrases related to truth and specific locations

    oai_token-act-pair · gpt-3.5-turbo

    concepts and terms related to truth and its implications in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ħ¢
    -0.71
     ende
    -0.67
    _.
    -0.65
    Reloaded
    -0.62
    etheless
    -0.61
    oyal
    -0.57
    pmwiki
    -0.57
    ãĥĥãĤ¯
    -0.55
     Rebell
    -0.54
    obin
    -0.54
    POSITIVE LOGITS
     bulletin
    0.61
    asia
    0.60
     tallest
    0.60
     Doors
    0.54
    station
    0.53
     Âł
    0.53
     âĸĪ
    0.52
     tents
    0.52
     Churches
    0.52
    OSED
    0.51
    Activations Density 1.474%

    No Known Activations