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. 5144
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals holding the title of "fellow" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the title "fellow."

    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
    ARA
    -0.73
    DEN
    -0.69
     DRAG
    -0.66
     Retrieved
    -0.66
     Archives
    -0.64
     Tycoon
    -0.63
     Sorceress
    -0.62
     Ukrain
    -0.62
    ADE
    -0.61
    onies
    -0.60
    POSITIVE LOGITS
    luaj
    0.84
    worldly
    0.82
    member
    0.81
     classmates
    0.78
    ference
    0.77
    brook
    0.76
     strugg
    0.76
     travellers
    0.76
    workers
    0.75
     traveler
    0.74
    Activations Density 0.008%

    No Known Activations