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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4489
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences that have the phrase "I can" followed by descriptions of action or ability

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "can" indicating potential or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edient
    -0.69
     Mant
    -0.67
    ependent
    -0.63
     Federation
    -0.62
    requisite
    -0.62
     Generation
    -0.61
     striving
    -0.59
    gement
    -0.58
    rams
    -0.58
     revision
    -0.58
    POSITIVE LOGITS
    't
    1.59
    adian
    1.15
    berra
    1.02
    NOT
    0.99
    isters
    0.88
    ister
    0.81
    ISTER
    0.81
    asta
    0.80
    nery
    0.79
    aden
    0.78
    Activations Density 0.178%

    No Known Activations