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. 18984
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inevitability or a certain outcome

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "a matter of time."

    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
    pps
    -0.78
    uras
    -0.72
    ovi
    -0.71
    notations
    -0.69
    Tur
    -0.67
    querade
    -0.66
    cci
    -0.66
     Guides
    -0.65
    luaj
    -0.64
    ako
    -0.64
    POSITIVE LOGITS
     sorts
    0.72
     luck
    0.71
     course
    0.69
     simmer
    0.68
     jurisdiction
    0.68
     justice
    0.66
     JUSTICE
    0.65
     whether
    0.65
     milliseconds
    0.64
    milo
    0.64
    Activations Density 0.047%

    No Known Activations