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. 7-RES-JB
    6. 15737
    Prev
    Next
    INDEX
    Explanations

    Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Vi" and its variations, suggesting a focus on something related to "VI" or "Viagra."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dress
    -0.76
    */(
    -0.74
    hesive
    -0.71
    WORK
    -0.67
    bread
    -0.67
    corn
    -0.65
    ivery
    -0.64
    lisher
    -0.64
    strap
    -0.64
    stro
    -0.63
    POSITIVE LOGITS
     versa
    0.87
    Äį
    0.86
    agra
    0.82
    uous
    0.79
    ISION
    0.78
    oodoo
    0.78
    ulner
    0.77
    iolet
    0.77
    isions
    0.76
    BuyableInstoreAndOnline
    0.74
    Activations Density 0.040%

    No Known Activations