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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 12-RES-JB
    6. 7000
    Prev
    Next
    INDEX
    Explanations

    information related to financial figures, contracts, and salaries in sports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    financial terms related to sports contracts and salaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atom
    -0.70
    devices
    -0.69
    cffffcc
    -0.66
    obyl
    -0.62
     Dictionary
    -0.62
     Mothers
    -0.61
     Answers
    -0.60
     Femin
    -0.59
     Mood
    -0.58
    femin
    -0.58
    POSITIVE LOGITS
     guaranteed
    0.99
     salary
    0.93
     roster
    0.90
     signing
    0.87
     bonus
    0.81
     base
    0.79
     annually
    0.77
    ilion
    0.77
    idy
    0.76
     bonuses
    0.76
    Activations Density 0.079%

    No Known Activations