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. 324
    Prev
    Next
    INDEX
    Explanations

    expressions of positive sentiment and acknowledgement

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing positive or negative sentiments about experiences and honors

    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
    untled
    -0.75
    krit
    -0.71
     objections
    -0.70
    è£
    -0.70
     deemed
    -0.67
    cum
    -0.67
    approved
    -0.65
    lite
    -0.64
    illary
    -0.63
    è¯
    -0.62
    POSITIVE LOGITS
     Grac
    0.78
     pity
    0.68
     rg
    0.66
     coincidence
    0.64
     bitters
    0.63
     Torrent
    0.62
     Crunch
    0.62
     Bren
    0.62
     Sturgeon
    0.61
     Yon
    0.61
    Activations Density 0.301%

    No Known Activations