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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 10056
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hibernation" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of fibers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pity
    -0.65
     undone
    -0.64
     Jung
    -0.64
     markup
    -0.61
     awe
    -0.61
     Shack
    -0.61
    words
    -0.59
    olulu
    -0.59
     Encounter
    -0.59
    ĸļ
    -0.59
    POSITIVE LOGITS
    iber
    1.37
    tarian
    1.03
    glass
    0.91
    tarians
    0.90
    ilib
    0.88
    glas
    0.84
    oad
    0.83
    ãĥ¼ãĤ¯
    0.81
     Fiber
    0.79
    culus
    0.78
    Activations Density 0.005%

    No Known Activations