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. 11449
    Prev
    Next
    INDEX
    Explanations

    references to checks or cheques, financial instruments used for payment

    oai_token-act-pair · gpt-3.5-turbo

    references to checks or payment methods

    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
     Archdemon
    -0.86
    ELF
    -0.76
    DragonMagazine
    -0.72
    Republic
    -0.69
    Assembly
    -0.69
    ãĤ¼
    -0.68
     Defenders
    -0.67
    ECT
    -0.67
    GGGGGGGG
    -0.66
    å§«
    -0.65
    POSITIVE LOGITS
    rolled
    0.97
    chet
    0.96
    ques
    0.91
    arest
    0.90
    ocobo
    0.89
    gee
    0.89
    ards
    0.88
    bag
    0.87
    bags
    0.85
    atted
    0.85
    Activations Density 0.009%

    No Known Activations