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. 0-RES-JB
    6. 17472
    Prev
    Next
    INDEX
    Explanations

    phrases related to unresolved issues or questions

    oai_token-act-pair · gpt-3.5-turbo

    references to the Kurdish Regional Government and concepts of unresolved issues or unanswered questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mits
    -0.82
    imer
    -0.71
    now
    -0.70
    ench
    -0.70
     Mog
    -0.69
     Buch
    -0.69
    uli
    -0.68
    cle
    -0.67
    heat
    -0.67
    cles
    -0.67
    POSITIVE LOGITS
    Ùĩ
    3.65
    KR
    1.53
     اÙĦ
    1.31
     unanswered
    1.13
    Ø©
    1.07
     KR
    0.94
     KH
    0.91
    ARI
    0.89
     Ùħ
    0.88
     EDITION
    0.86
    Activations Density 0.047%

    No Known Activations