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. 11625
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the news outlet "RT"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "RT," likely indicating retweets or references to other sources in social media 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
    iasis
    -0.84
    ãĤ©
    -0.68
    tained
    -0.67
    alities
    -0.67
    rera
    -0.65
    erved
    -0.63
     coron
    -0.62
     incent
    -0.62
     [|
    -0.61
    cised
    -0.61
    POSITIVE LOGITS
    Ãī
    1.14
    irtual
    0.89
    TY
    0.82
    PC
    0.80
    TE
    0.80
    IA
    0.79
    BF
    0.78
    ython
    0.78
    LM
    0.77
    RT
    0.77
    Activations Density 0.014%

    No Known Activations