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. 10-RES-JB
    6. 14836
    Prev
    Next
    INDEX
    Explanations

    phrases containing the phrase "kind of"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating similarity or analogy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ests
    -0.81
    ESE
    -0.80
    uers
    -0.79
    ULTS
    -0.78
    senal
    -0.77
    Fs
    -0.76
    ãĥĭ
    -0.76
    ourses
    -0.74
    iership
    -0.74
    umerable
    -0.73
    POSITIVE LOGITS
     messed
    0.97
     screwed
    0.97
     fucked
    0.90
     neat
    0.88
     ironic
    0.86
     bum
    0.86
     sucked
    0.86
     weird
    0.83
     goofy
    0.82
     boring
    0.82
    Activations Density 0.050%

    No Known Activations