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. 11-RES-JB
    6. 8101
    Prev
    Next
    INDEX
    Explanations

    instances where someone is making a judgment or taking an action based on a specific reason or belief

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to justification or rationale for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     redes
    -0.72
     exting
    -0.71
    odge
    -0.69
    puter
    -0.68
    ãĥĥãĥĪ
    -0.62
    quer
    -0.62
    ilet
    -0.62
    foundland
    -0.60
    exclusive
    -0.60
    isSpecial
    -0.60
    POSITIVE LOGITS
     of
    1.23
     they
    1.09
     THEY
    1.02
     somebody
    0.99
    of
    0.97
     thereof
    0.97
     someone
    0.95
     OF
    0.92
     Of
    0.91
     we
    0.89
    Activations Density 0.069%

    No Known Activations