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. 24539
    Prev
    Next
    INDEX
    Explanations

    information related to specific event details like dates, locations, and participants

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and locations related to 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
     positives
    -0.48
    earchers
    -0.42
     faint
    -0.41
    */(
    -0.41
     bats
    -0.41
     meanwhile
    -0.41
     survives
    -0.40
     contradictory
    -0.40
    hematically
    -0.40
    paio
    -0.40
    POSITIVE LOGITS
     Junction
    0.50
     Strait
    0.46
     Ely
    0.46
    ember
    0.46
     Exhibition
    0.45
     Albany
    0.44
     Elys
    0.44
     Quarter
    0.44
     Gw
    0.43
     Trent
    0.43
    Activations Density 1.523%

    No Known Activations