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. 9886
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Moff"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Moff" and variations of it

    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
    boarding
    -0.64
     nationalist
    -0.62
     IMAGES
    -0.62
    Enlarge
    -0.61
    zanne
    -0.61
     fateful
    -0.61
     folding
    -0.61
     Haitian
    -0.60
     martial
    -0.60
    1800
    -0.60
    POSITIVE LOGITS
     Moff
    1.41
     Osw
    0.88
    abit
    0.86
    ett
    0.86
    adish
    0.82
    ules
    0.81
    idge
    0.81
    inson
    0.80
    STON
    0.79
    atis
    0.76
    Activations Density 0.010%

    No Known Activations