Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 8883
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional statements using 'if'

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements that begin with "if"

    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
    ãĤª
    -0.74
    omi
    -0.67
    ocker
    -0.61
    akia
    -0.61
    Eye
    -0.61
    kay
    -0.60
     Roses
    -0.60
    axy
    -0.60
    isal
    -0.60
     Nationwide
    -0.59
    POSITIVE LOGITS
    fy
    1.10
    rame
    0.98
     they
    0.89
    soever
    0.87
     you
    0.81
    ornia
    0.80
    tar
    0.78
     unchecked
    0.74
     someone
    0.71
     anyone
    0.70
    Activations Density 0.104%

    No Known Activations