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. 10552
    Prev
    Next
    INDEX
    Explanations

    chemical elements or compounds

    oai_token-act-pair · gpt-3.5-turbo

    references to "Tr" or related numeric terms indicating a specific classification or categorization

    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
    MENTS
    -0.73
    ELS
    -0.72
    ãģ®éŃĶ
    -0.71
     Mechdragon
    -0.69
    lihood
    -0.68
    WARE
    -0.67
    EStream
    -0.67
    manship
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
    BILITIES
    -0.64
    POSITIVE LOGITS
    ainer
    1.16
    ains
    1.04
    ained
    1.04
    izoph
    1.03
    ilateral
    1.02
    unn
    1.01
    umps
    1.00
    unk
    1.00
    unks
    1.00
    itton
    0.99
    Activations Density 0.014%

    No Known Activations