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. 3379
    Prev
    Next
    INDEX
    Explanations

    references to a basketball court

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or context related to sports, particularly basketball courts

    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
     sow
    -0.68
    resso
    -0.64
     Petro
    -0.62
    OPLE
    -0.62
     elector
    -0.59
     municipality
    -0.58
    iments
    -0.58
     Leone
    -0.57
     Univers
    -0.57
     Bundes
    -0.57
    POSITIVE LOGITS
    esan
    1.05
    auld
    0.95
    stall
    0.93
    headers
    0.89
    rooms
    0.87
    frames
    0.85
    anova
    0.83
    room
    0.80
    breakers
    0.79
    wright
    0.78
    Activations Density 0.040%

    No Known Activations