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. 3-RES-JB
    6. 19521
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "sey" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "sey."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.72
     tense
    -0.71
     analges
    -0.68
    66666666
    -0.66
    CVE
    -0.64
     PKK
    -0.64
     wildfire
    -0.63
    HAHAHAHA
    -0.63
    agonist
    -0.62
     supplies
    -0.61
    POSITIVE LOGITS
    sey
    1.27
    yk
    0.94
    eah
    0.89
    dale
    0.82
    orkshire
    0.80
    ety
    0.79
    seys
    0.78
    onduct
    0.77
    udo
    0.77
    ez
    0.77
    Activations Density 0.010%

    No Known Activations