Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 23005
    Prev
    Next
    INDEX
    Explanations

    phrases related to recurring time intervals

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "every" 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
    phabet
    -0.73
    olas
    -0.71
    zai
    -0.70
    dict
    -0.66
     Osw
    -0.66
     Viz
    -0.63
     Sakuya
    -0.62
    rawdownloadcloneembedreportprint
    -0.62
     notwithstanding
    -0.61
     Jah
    -0.61
    POSITIVE LOGITS
    THING
    1.37
    where
    1.11
     conceivable
    1.04
    things
    1.00
    single
    0.96
     imaginable
    0.95
     single
    0.90
    WHERE
    0.87
    Ĥª
    0.86
    body
    0.81
    Activations Density 0.046%

    No Known Activations