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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 14721
    Prev
    Next
    INDEX
    Explanations

    words related to age groups, specifically focusing on children aged 5 and under

    oai_token-act-pair · gpt-3.5-turbo

    references to age groups and family dynamics

    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
    fax
    -0.72
     Citiz
    -0.68
    ãĤ§
    -0.68
    Fall
    -0.67
    ipher
    -0.66
    atin
    -0.66
    MAL
    -0.64
    akin
    -0.64
    antha
    -0.62
    rar
    -0.61
    POSITIVE LOGITS
     microphones
    0.67
     extraord
    0.61
     fame
    0.59
    ãĢĤ
    0.59
     budgets
    0.58
     talents
    0.57
     assistants
    0.57
    .[
    0.55
    UGE
    0.54
     cuisine
    0.54
    Activations Density 0.528%

    No Known Activations