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. 19221
    Prev
    Next
    INDEX
    Explanations

    references to the word "Gay" - potentially indicating a focus on a specific person or topic named "Gay"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "Gay."

    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
    KT
    -0.84
    ocobo
    -0.81
    è¦ļéĨĴ
    -0.79
    éĹĺ
    -0.77
    âĵĺ
    -0.74
    arily
    -0.74
    ACTED
    -0.72
    aeda
    -0.72
    etsk
    -0.70
    igslist
    -0.70
    POSITIVE LOGITS
    atri
    1.00
    bian
    0.97
     Gay
    0.95
    lord
    0.94
    dar
    0.92
    lyn
    0.89
    zilla
    0.85
    nor
    0.85
    ety
    0.84
    cott
    0.83
    Activations Density 0.005%

    No Known Activations