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. 15460
    Prev
    Next
    INDEX
    Explanations

    names related to the surname "Attenborough"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals associated with media and events

    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
    adelphia
    -0.71
    theless
    -0.68
     thirds
    -0.64
     halves
    -0.64
    ÅĤ
    -0.63
     continents
    -0.62
     decaying
    -0.61
     Anat
    -0.60
    pher
    -0.60
     wast
    -0.58
    POSITIVE LOGITS
    achment
    0.95
    oola
    0.81
    ainment
    0.80
    urai
    0.75
    itiveness
    0.75
    FN
    0.73
    Footnote
    0.70
    ractive
    0.68
    enza
    0.68
    ãĤ¤ãĥĪ
    0.67
    Activations Density 0.136%

    No Known Activations