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. 14440
    Prev
    Next
    INDEX
    Explanations

    phrases including the substring "tra" which may often relate to words like "traffic", "traumatic", "trailers", and "transfer"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "trait" or its variations

    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
     Pwr
    -0.77
    amental
    -0.73
    manship
    -0.65
     Seym
    -0.62
     Mortal
    -0.62
    lihood
    -0.62
     OK
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    lists
    -0.59
    MODE
    -0.59
    POSITIVE LOGITS
    quel
    1.00
    pez
    0.98
    pped
    0.93
    umat
    0.93
    umatic
    0.93
    verse
    0.92
    itored
    0.91
    ffic
    0.91
    pping
    0.90
    ppings
    0.89
    Activations Density 0.016%

    No Known Activations