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. 6-RES-JB
    6. 19371
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the intended purpose or target audience of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "intended" and phrases related to purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tex
    -0.78
     Solitaire
    -0.75
    yards
    -0.75
     Leone
    -0.66
    ced
    -0.63
    oner
    -0.62
    java
    -0.62
    ranked
    -0.61
    las
    -0.61
    Du
    -0.61
    POSITIVE LOGITS
     Parenthood
    0.89
     beneficiaries
    0.78
     recipients
    0.76
    fully
    0.71
     intended
    0.69
     beneficiary
    0.69
     recipient
    0.67
     audience
    0.66
    ãĥĻ
    0.66
    ividual
    0.66
    Activations Density 0.028%

    No Known Activations