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. 306
    Prev
    Next
    INDEX
    Explanations

    phrases related to statehood

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships and concepts of "hood" such as fatherhood, motherhood, and statehood

    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
    abase
    -0.81
    chnology
    -0.75
     FANTASY
    -0.68
     WATCHED
    -0.67
     DEF
    -0.63
    ngth
    -0.61
    NRS
    -0.61
    orno
    -0.61
    ALK
    -0.60
    ERC
    -0.60
    POSITIVE LOGITS
    sie
    0.93
    hood
    0.90
    mares
    0.79
    s
    0.76
    itus
    0.75
    warming
    0.74
    enture
    0.74
    stones
    0.73
    oos
    0.72
    edly
    0.72
    Activations Density 0.019%

    No Known Activations