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. 10564
    Prev
    Next
    INDEX
    Explanations

    words related to negative emotions, such as discontent, dissatisfaction, and disillusionment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dissatisfaction and feelings of discontent

    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
    ramid
    -0.91
    obal
    -0.74
    sites
    -0.71
    icrobial
    -0.70
    fman
    -0.69
    opa
    -0.68
    ahead
    -0.68
    estone
    -0.67
    zyme
    -0.67
    onut
    -0.66
    POSITIVE LOGITS
     dissatisfied
    0.92
     discont
    0.90
     dissatisfaction
    0.81
     disillusion
    0.80
     unhappy
    0.80
     frustrations
    0.79
     Anger
    0.75
     discontent
    0.75
     disple
    0.74
     displeasure
    0.74
    Activations Density 0.032%

    No Known Activations