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. 12-RES-JB
    6. 15213
    Prev
    Next
    INDEX
    Explanations

    words related to corporate governance and financial matters

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

    terms related to corporate entities and their activities

    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
    lest
    -0.81
    imen
    -0.76
    mith
    -0.75
    lyn
    -0.73
    older
    -0.73
    ounds
    -0.71
    imental
    -0.71
    yna
    -0.68
    emb
    -0.67
    ggies
    -0.67
    POSITIVE LOGITS
     governance
    0.99
     espionage
    0.94
     welfare
    0.94
     America
    0.84
     sponsorship
    0.83
     profits
    0.83
     restructuring
    0.81
     welf
    0.80
     earnings
    0.80
     wellness
    0.80
    Activations Density 0.053%

    No Known Activations