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. 8-RES-JB
    6. 19669
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Ari"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ari" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sung
    -0.73
    ted
    -0.73
     tremend
    -0.70
    rified
    -0.69
    vertisement
    -0.69
    lasses
    -0.68
    fulness
    -0.68
    mort
    -0.67
    hops
    -0.66
    umbledore
    -0.66
    POSITIVE LOGITS
    yah
    1.07
    ya
    1.04
    Äĩ
    1.00
    ño
    0.96
     Vaj
    0.89
    YA
    0.83
    ksh
    0.80
    ennes
    0.79
    ón
    0.79
    yy
    0.78
    Activations Density 0.054%

    No Known Activations