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. 15550
    Prev
    Next
    INDEX
    Explanations

    texts enclosed by the word "Cont"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "cont" indicating potential content-related discussions or references

    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
    EStream
    -0.95
    ħĭ
    -0.83
    lihood
    -0.80
    terday
    -0.78
    STER
    -0.77
    OPLE
    -0.75
    UGE
    -0.74
    manship
    -0.67
    GBT
    -0.67
    WT
    -0.66
    POSITIVE LOGITS
    ributed
    1.24
    ainment
    1.19
    ainers
    1.19
    rast
    1.15
    ribution
    1.14
    roversial
    1.12
    rary
    1.09
    ribute
    1.07
    acts
    1.06
    rovers
    1.03
    Activations Density 0.016%

    No Known Activations