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. 18998
    Prev
    Next
    INDEX
    Explanations

    words related to news articles and online content

    oai_token-act-pair · gpt-3.5-turbo

    the letter "S" in various contexts

    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
     techno
    -0.69
     bottleneck
    -0.68
    EStream
    -0.67
     unrestricted
    -0.67
     CPR
    -0.67
     laureate
    -0.66
    catentry
    -0.65
    puter
    -0.65
     crib
    -0.65
     downed
    -0.64
    POSITIVE LOGITS
    AND
    1.18
    OUND
    1.18
    ESSION
    1.16
    UD
    1.12
    ustain
    1.12
    UM
    1.12
    RS
    1.10
    WE
    1.10
    ELF
    1.08
    UR
    1.06
    Activations Density 0.045%

    No Known Activations