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. 0-RES-JB
    6. 743
    Prev
    Next
    INDEX
    Explanations

    words related to schemes or scheming

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ming," which relates to managing or organizing various activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sector
    -0.67
     Camden
    -0.63
     accountable
    -0.58
     Charity
    -0.56
     Region
    -0.55
    ����
    -0.55
     doubtful
    -0.55
     Crisis
    -0.54
     Finch
    -0.54
     carrot
    -0.54
    POSITIVE LOGITS
    ming
    4.45
    med
    2.29
    mers
    2.00
    mer
    1.78
    mes
    1.53
    bing
    1.50
    ms
    1.47
    ting
    1.40
    mable
    1.38
    ding
    1.36
    Activations Density 0.011%

    No Known Activations