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. 0-RES-JB
    6. 3136
    Prev
    Next
    INDEX
    Explanations

    words with an 'iz' ending

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the suffix "iz."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cables
    -0.65
     Kirst
    -0.64
     CHRIST
    -0.60
     Por
    -0.60
     grou
    -0.60
     duly
    -0.59
     packets
    -0.59
     Claud
    -0.58
     jumper
    -0.58
     coupled
    -0.58
    POSITIVE LOGITS
    iz
    4.30
    IZ
    2.38
    iza
    2.19
    izo
    1.89
    izz
    1.76
    izable
    1.63
    izer
    1.52
    iaz
    1.49
    ize
    1.49
    izu
    1.46
    Activations Density 0.019%

    No Known Activations