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. 21511
    Prev
    Next
    INDEX
    Explanations

    mentions of financial transactions or budget-related discussions

    oai_token-act-pair · gpt-3.5-turbo

    sections indicating significant financial transactions or funding discussions

    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
     adolesc
    -0.88
     civilisation
    -0.87
     endeavour
    -0.86
     regenerate
    -0.82
    utic
    -0.81
     realised
    -0.77
     fulfil
    -0.76
     paed
    -0.76
     Reincarnated
    -0.75
     whilst
    -0.74
    POSITIVE LOGITS
    Newsletter
    1.24
    Washington
    1.11
    Story
    1.06
    Advertisement
    1.04
    Iowa
    1.03
    Still
    1.02
    Specifically
    1.02
    Wisconsin
    1.02
    Bloomberg
    1.01
    Asked
    0.99
    Activations Density 0.786%

    No Known Activations