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. 12646
    Prev
    Next
    INDEX
    Explanations

    phrases related to natural disasters or environmental events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tidal patterns and conditions

    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
    ioned
    -0.91
    enegger
    -0.84
    raised
    -0.83
    skirts
    -0.80
    raising
    -0.79
    orate
    -0.77
    oken
    -0.77
    ĸļ
    -0.76
    ronic
    -0.74
    ebin
    -0.73
    POSITIVE LOGITS
    idal
    0.95
    band
    0.76
    ves
    0.74
     pend
    0.74
     Veil
    0.69
    adoes
    0.68
     Castro
    0.66
    glass
    0.66
    ysis
    0.66
    phia
    0.66
    Activations Density 0.027%

    No Known Activations