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. 6541
    Prev
    Next
    INDEX
    Explanations

    phrases related to the use of specific items or products, particularly with focus on prices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to energy sources, specifically coal, and expressions of concern or complexity regarding various topics

    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
    ocious
    -0.67
    blance
    -0.60
     millenn
    -0.59
     conclud
    -0.56
    asonable
    -0.56
    ļé
    -0.55
    ascript
    -0.55
     proport
    -0.53
     Vaugh
    -0.52
    itious
    -0.51
    POSITIVE LOGITS
     cz
    0.47
    Ĥİ
    0.47
     Bast
    0.47
     Jackets
    0.46
     Bre
    0.46
     Cinema
    0.45
    hardt
    0.45
     Skip
    0.44
     Bin
    0.44
     AAA
    0.43
    Activations Density 1.202%

    No Known Activations