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. 8-RES-JB
    6. 8873
    Prev
    Next
    INDEX
    Explanations

    keywords related to professionalism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "professional" in relation to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edin
    -0.82
    apo
    -0.77
    erella
    -0.72
    bolt
    -0.70
    ource
    -0.69
    _>
    -0.68
    attr
    -0.68
    anus
    -0.67
    combe
    -0.66
    pots
    -0.65
    POSITIVE LOGITS
     wrestler
    1.08
     athlete
    1.00
     athletes
    0.95
     footballer
    0.94
     wrestling
    0.93
     gol
    0.93
    ized
    0.92
    digy
    0.89
    ising
    0.89
     Wrest
    0.86
    Activations Density 0.037%

    No Known Activations