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. 3781
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with "Ts"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tsunami

    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
    nesota
    -0.82
    SOURCE
    -0.75
    liness
    -0.74
    naissance
    -0.74
    ãĥ¼ãĥĨ
    -0.72
    EEE
    -0.71
    heid
    -0.70
    tained
    -0.69
    ously
    -0.69
    heads
    -0.68
    POSITIVE LOGITS
    izoph
    1.06
    ouk
    0.99
    avorite
    0.99
    arnaev
    0.96
    omp
    0.88
    onic
    0.87
    annis
    0.86
    unin
    0.85
    ug
    0.85
    onga
    0.85
    Activations Density 0.006%

    No Known Activations