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. 6-RES-JB
    6. 3157
    Prev
    Next
    INDEX
    Explanations

    names or terms with the phonetic sound "ay"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Ay" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipeg
    -0.86
    ãĤ´ãĥ³
    -0.74
    hester
    -0.71
     Archdemon
    -0.70
    ugal
    -0.68
    女
    -0.67
    urally
    -0.64
     mund
    -0.64
    ãĥĦ
    -0.63
    ãĤ¢ãĥ«
    -0.63
    POSITIVE LOGITS
    alam
    0.92
    cott
    0.89
    atana
    0.83
    nor
    0.81
    walk
    0.79
    onet
    0.79
    rand
    0.79
    yy
    0.79
    tes
    0.78
    nard
    0.77
    Activations Density 0.042%

    No Known Activations