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. 9764
    Prev
    Next
    INDEX
    Explanations

    the name "Paulette" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "roulette."

    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
    ilities
    -0.77
    taboola
    -0.74
    ĻĤ
    -0.74
    iary
    -0.73
    rises
    -0.72
    rise
    -0.70
    ORE
    -0.69
    itu
    -0.69
    iaries
    -0.68
    ulates
    -0.66
    POSITIVE LOGITS
    lette
    1.51
    ttes
    0.98
    hammer
    0.90
    lli
    0.87
    lla
    0.85
    Mania
    0.84
    llo
    0.82
     Goldberg
    0.80
     Goddard
    0.79
    pload
    0.77
    Activations Density 0.007%

    No Known Activations