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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 24124
    Prev
    Next
    INDEX
    Explanations

    specifications and names related to technology, likely focusing on abbreviations or acronyms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Ps," which likely refers to a specific medical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.74
     cookie
    -0.67
     straw
    -0.65
     square
    -0.62
     Venice
    -0.62
     tail
    -0.62
     boiler
    -0.62
     locker
    -0.61
     university
    -0.60
     school
    -0.59
    POSITIVE LOGITS
    Ps
    4.46
     Ps
    2.02
    Ts
    1.46
     ps
    1.40
    Ms
    1.38
    Fs
    1.37
    Cs
    1.36
    Vs
    1.36
    Ns
    1.35
    Os
    1.35
    Activations Density 0.008%

    No Known Activations