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. 9454
    Prev
    Next
    INDEX
    Explanations

    references to historical events or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to historical or geographical locations, particularly identifying places or significant events related to ancient or past civilizations

    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
    èª
    -0.75
    SPONSORED
    -0.67
    cue
    -0.64
     Debor
    -0.64
     Bowen
    -0.62
     TA
    -0.59
    Feed
    -0.58
    aldehyde
    -0.58
     manager
    -0.58
    opic
    -0.55
    POSITIVE LOGITS
    illion
    0.97
    apo
    0.78
    pees
    0.78
    akh
    0.76
    ailability
    0.71
     livest
    0.68
    ilion
    0.68
    asse
    0.67
    omez
    0.66
    roc
    0.66
    Activations Density 0.133%

    No Known Activations