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. 2-RES-JB
    6. 2201
    Prev
    Next
    INDEX
    Explanations

    references to the number 50

    oai_token-act-pair · gpt-3.5-turbo

    references to the number 50

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ller
    -0.81
    hunt
    -0.79
    kell
    -0.70
    ilic
    -0.68
     teased
    -0.68
    hiba
    -0.67
    unct
    -0.66
    velt
    -0.65
     tension
    -0.65
    alyses
    -0.64
    POSITIVE LOGITS
     Shades
    1.14
    %-
    1.09
    %"
    1.07
     cents
    1.03
    %;
    1.00
    ¢
    0.96
    %
    0.94
    percent
    0.89
    ishers
    0.89
    %:
    0.88
    Activations Density 0.027%

    No Known Activations