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. 3892
    Prev
    Next
    INDEX
    Explanations

    the word "this."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific moments or contexts in 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
    sylv
    -0.65
    keeper
    -0.64
    kens
    -0.61
    ratulations
    -0.61
    STEM
    -0.60
    scape
    -0.59
    ghan
    -0.59
    gre
    -0.58
    keepers
    -0.58
    ilies
    -0.57
    POSITIVE LOGITS
     behest
    1.21
     expense
    1.04
     outset
    1.03
     intersections
    0.96
     helm
    0.93
     discretion
    0.91
     insistence
    0.87
     glance
    0.86
     concess
    0.82
     speeds
    0.81
    Activations Density 0.142%

    No Known Activations