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. 4356
    Prev
    Next
    INDEX
    Explanations

    phrases related to the ongoing or unfolding of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases discussing the progression or unfolding of events

    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
    shaw
    -0.76
     Sho
    -0.68
     Lou
    -0.63
    ery
    -0.62
     Core
    -0.61
     Metallic
    -0.61
     selector
    -0.60
     Younger
    -0.58
    eries
    -0.58
     Mub
    -0.58
    POSITIVE LOGITS
    casts
    0.92
    fitted
    0.89
    lived
    0.85
    stretched
    0.80
    wards
    0.76
    posts
    0.75
    flows
    0.73
    skirts
    0.71
    number
    0.70
     Aval
    0.70
    Activations Density 0.051%

    No Known Activations