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. 5-RES-JB
    6. 2087
    Prev
    Next
    INDEX
    Explanations

    phrases expressing negative emotions or unfortunate situations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sorrow or regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afort
    -0.82
    uese
    -0.81
     newsp
    -0.79
    insula
    -0.78
    amins
    -0.76
    enture
    -0.74
    ual
    -0.73
    uality
    -0.72
     Gutenberg
    -0.71
    itives
    -0.71
    POSITIVE LOGITS
     sadly
    0.79
    à¥
    0.78
    ãĥ©ãĥ³
    0.73
    ãĤ´ãĥ³
    0.73
     parted
    0.70
    ãĥIJ
    0.70
    510
    0.70
     displayed
    0.69
    ा
    0.69
    stal
    0.67
    Activations Density 0.024%

    No Known Activations