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. 15935
    Prev
    Next
    INDEX
    Explanations

    mentions of repealing or canceling laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of repeal

    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
     guiActiveUnfocused
    -0.97
     Harrington
    -0.70
    doms
    -0.67
     OPS
    -0.65
    heid
    -0.63
     Fraser
    -0.62
     seas
    -0.62
     Improvement
    -0.61
     Ops
    -0.60
     Io
    -0.60
    POSITIVE LOGITS
    aters
    1.29
    ating
    1.23
    ety
    1.16
    lling
    1.15
    ated
    1.11
    ater
    1.11
    issance
    1.06
    eter
    1.03
    aling
    1.00
    encer
    0.99
    Activations Density 0.024%

    No Known Activations