Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 19911
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of professional roles or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edin
    -0.82
    anus
    -0.76
    apo
    -0.76
    stant
    -0.71
    adr
    -0.71
    appropriately
    -0.70
    orious
    -0.69
    ource
    -0.69
    erella
    -0.69
    rams
    -0.67
    POSITIVE LOGITS
     wrestler
    1.23
     footballer
    1.10
     wrestling
    1.09
     athlete
    1.06
     gol
    1.02
     athletes
    1.00
    ized
    0.95
     soccer
    0.94
     sports
    0.93
     wrestlers
    0.92
    Activations Density 0.029%

    No Known Activations