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. 20487
    Prev
    Next
    INDEX
    Explanations

    words related to something long-lasting or enduring

    oai_token-act-pair · gpt-3.5-turbo

    references to enduring or long-lasting effects and impacts

    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
    ramid
    -1.04
    alon
    -1.01
     Cosponsors
    -0.95
    aucus
    -0.86
    ologies
    -0.82
    ioch
    -0.78
    ses
    -0.78
    alion
    -0.77
    umbn
    -0.77
    riad
    -0.75
    POSITIVE LOGITS
     lasting
    1.09
     adolesc
    0.89
    lasting
    0.82
    Effects
    0.81
     consequences
    0.80
     isot
    0.79
     memories
    0.77
     effects
    0.77
    åĬ
    0.77
     gratification
    0.73
    Activations Density 0.018%

    No Known Activations