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. 15641
    Prev
    Next
    INDEX
    Explanations

    phrases that end with an emphatic expression

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of 'it's' as a contraction of 'it is.'

    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
     mathemat
    -0.81
     carbohyd
    -0.78
    raviolet
    -0.76
    odium
    -0.73
     satell
    -0.71
     tremend
    -0.71
    ourgeois
    -0.70
     elim
    -0.70
    geries
    -0.68
    hift
    -0.68
    POSITIVE LOGITS
    ï¸ı
    0.87
    女
    0.86
    ··
    0.81
    ¯
    0.79
    ãģ®éŃĶ
    0.79
     âĢ
    0.76
    ãĤĭ
    0.75
    Äĩ
    0.75
    ¯¯¯¯
    0.74
    head
    0.72
    Activations Density 0.238%

    No Known Activations