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. 8-RES-JB
    6. 8913
    Prev
    Next
    INDEX
    Explanations

    words related to the video game series "Mass Effect."

    oai_token-act-pair · gpt-3.5-turbo

    the term "Mass" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stal
    -0.74
    gered
    -0.67
    gery
    -0.65
    thens
    -0.64
     unfit
    -0.63
     pony
    -0.63
     Bil
    -0.62
     Bosnia
    -0.62
     Tayyip
    -0.62
    merce
    -0.60
    POSITIVE LOGITS
    achus
    1.33
    achusetts
    1.26
    acre
    1.12
    imil
    1.02
    achu
    0.91
    igation
    0.86
    olini
    0.85
    ieu
    0.83
    ilia
    0.80
    arella
    0.79
    Activations Density 0.020%

    No Known Activations