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. 13678
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or happiness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement or strong positive emotions

    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
    •layer 5 - happiness

    No Comments

    Negative Logits
    ciplinary
    -0.85
    poral
    -0.81
    enhagen
    -0.78
    road
    -0.78
    lay
    -0.73
    icrobial
    -0.72
    dule
    -0.70
    sterdam
    -0.68
    prison
    -0.67
    icipated
    -0.67
    POSITIVE LOGITS
     exclaim
    0.72
    ION
    0.69
     exclaimed
    0.67
     VID
    0.66
     delight
    0.65
    iously
    0.64
     delighted
    0.64
     Euros
    0.64
     Romeo
    0.64
    ÃįÃį
    0.64
    Activations Density 0.049%

    No Known Activations